Showing 1–50 of 95 results for author: Gray, A

LoRIS: LoRaWAN-based IoT Platform for Sustainability Monitoring in Hotels

Authors: Yash Pandey, Angus Gray, Reza Serati, Oscar Zhu, Emil Juvan, Anna Zinn, Danyelle Greene, Qingqing Chen, Sarah MacInnes, Siamak Layeghy, Sara Dolnicar, Marius Portmann

Abstract: The hospitality sector is a major source of global greenhouse gas emissions, water stress, and waste generation, yet sustainability reporting in hotels remains constrained by coarse, manually collected operational data. We present LoRIS (LoRaWAN-based IoT platform for sustainability monitoring in hotels), a LoRaWAN-based sensing system that delivers high-resolution measurements of resource consump… ▽ More The hospitality sector is a major source of global greenhouse gas emissions, water stress, and waste generation, yet sustainability reporting in hotels remains constrained by coarse, manually collected operational data. We present LoRIS (LoRaWAN-based IoT platform for sustainability monitoring in hotels), a LoRaWAN-based sensing system that delivers high-resolution measurements of resource consumption, environmental conditions, and guest behaviour across geographically distributed hotel properties. The architecture follows the canonical LoRaWAN reference model and is built for the operational realities of hospitality deployments: restrictive hotel IT policies, guest privacy expectations, rapid and reversible installation, and multi-year battery operation. Privacy-by-design guides modality selection and deployment zoning, and end-to-end encryption protects data from sensor to dashboard. This system has been running since February 2022 and currently spans 850 sensors of 19 types across 21 sites in Australia and Slovenia, covering both the AU915 and EU868 regulatory regions. The platform has generated over 202 million sensor records and ingests approximately 245,000 uplink messages per day on managed serverless infrastructure. Our system has been successfully used for seven field studies spanning food waste, energy consumption, and water consumption, including controlled intervention experiments that measure environmental outcomes and guest satisfaction in parallel. This system shows that LoRaWAN sensing can be deployed at scale in operational hotels without compromising guest experience or privacy. △ Less

Submitted 18 August, 2026; originally announced August 2026.

Recover, Discover, Plan: Learning Skills and Concepts from Robot Failures

Authors: Bowen Li, Mayank Mishra, Y. Isabel Liu, Stone Tao, Nishanth Kumar, Alexander G. Gray, Ruwan Wickramarachchi, Jonathan Francis, Sebastian Scherer, Tom Silver

Abstract: Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoid them in the future. While reinforcement learning (RL) can learn reactive recovery behaviors, training a separate policy for every distinct failure mode is highly inefficient. We introduce Recovery-Driven Synthesis of Relational Concepts (ReSYNC), the first approach that progressively d… ▽ More Intelligent robots should not only recover from failures, but also acquire the abstract knowledge needed to avoid them in the future. While reinforcement learning (RL) can learn reactive recovery behaviors, training a separate policy for every distinct failure mode is highly inefficient. We introduce Recovery-Driven Synthesis of Relational Concepts (ReSYNC), the first approach that progressively discovers and refines state abstractions (relational predicates) from failure-recovery experience to support abstract planning. Unlike purely reactive methods, ReSYNC jointly learns skills and concepts through an incremental dual-learning process. In the skill-learning phase, the robot uses RL to learn to recover from failures seen in training tasks. In the concept-learning phase, the robot discovers new relational predicates and refines its abstract planning model to explain and generalize the learned recovery behaviors. This interaction enables ReSYNC to convert local recoveries seen during training into global failure avoidance at test time. Across four simulated domains, we show that ReSYNC's ability to continually expand and refine its abstraction library allows it to solve long-horizon, previously unseen problems, outperforming strong baselines by over 50%. Additionally, we demonstrate sim-to-real transfer of ReSYNC, where it performs real-world non-prehensile manipulation skills and generalizes to unseen scenarios through abstract planning. Overall, ReSYNC represents a significant step toward robots that autonomously acquire abstractions for scalable, failure-aware planning in the physical world. △ Less

Submitted 16 June, 2026; originally announced June 2026.

Comments: 9 pages, 6 figures. Website: https://jaraxxus-me.github.io/ReSYNC/

Transformers Can Learn Rules They've Never Seen: Proof of Computation Beyond Interpolation

Authors: Andy Gray

Abstract: A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only interpolate: predict new cases from their similarity to training examples. We test this in a controlled setting where interpolation provably fails, so success can only come from computation beyond interpolation. We train small transformers to predict th… ▽ More A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only interpolate: predict new cases from their similarity to training examples. We test this in a controlled setting where interpolation provably fails, so success can only come from computation beyond interpolation. We train small transformers to predict the rollout of a cellular automaton whose update rule is pure XOR, and remove one entry of the rule's truth table from all direct supervision. The missing entry's output is never shown to the model; its only trace is indirect, as wrong values corrupt visible predictions at later timesteps. Because XOR parity flips whenever one input bit is changed, every one-bit neighbour of the missing entry carries the opposite label, and we prove that similarity-based predictors, including nearest-neighbour, kernel, and Gaussian-process methods, are forced to the wrong answer. A two-layer transformer can nevertheless recover the missing entry, and circuit extraction confirms it computes XOR exactly. Ablations show the recovery depends on gradient signal propagating through multi-step prediction, and a second, structurally unrelated benchmark on symbolic operator chains exhibits the same capacity under ordinary autoregressive training. Together with a constructive proof that a standard transformer block can implement exact local Boolean rules, these results provide an existence proof that transformers can learn rule structure not directly observed in training and express it explicitly. This rules out the strongest architectural form of the interpolation-only account, the claim that transformers cannot in principle discover and communicate unseen rules, while leaving open when such behaviour arises in large-scale language training. △ Less

Submitted 29 July, 2026; v1 submitted 17 March, 2026; originally announced March 2026.

Comments: 28 pages, 6 figures

Learning Physical Operators using Neural Operators

Authors: Vignesh Gopakumar, Ander Gray, Dan Giles, Lorenzo Zanisi, Matt J. Kusner, Timo Betcke, Stanislas Pamela, Marc Peter Deisenroth

Abstract: Neural operators have emerged as promising surrogate models for solving partial differential equations (PDEs), but struggle to generalise beyond training distributions and are often constrained to a fixed temporal discretisation. This work introduces a physics-informed training framework that addresses these limitations by decomposing PDEs using operator splitting methods, training separate neural… ▽ More Neural operators have emerged as promising surrogate models for solving partial differential equations (PDEs), but struggle to generalise beyond training distributions and are often constrained to a fixed temporal discretisation. This work introduces a physics-informed training framework that addresses these limitations by decomposing PDEs using operator splitting methods, training separate neural operators to learn individual non-linear physical operators while approximating linear operators with fixed finite-difference convolutions. This modular mixture-of-experts architecture enables generalisation to novel physical regimes by explicitly encoding the underlying operator structure. We formulate the modelling task as a neural ordinary differential equation (ODE) where these learned operators constitute the right-hand side, enabling continuous-in-time predictions through standard ODE solvers and implicitly enforcing PDE constraints. Demonstrated on incompressible and compressible Navier--Stokes equations, our approach achieves better convergence and superior performance when generalising to unseen physics. The method remains parameter-efficient, enabling temporal extrapolation beyond training horizons, and provides interpretable components whose behaviour can be verified against known physics. △ Less

Submitted 2 April, 2026; v1 submitted 26 February, 2026; originally announced February 2026.

Unifying Deep Predicate Invention with Pre-trained Foundation Models

Authors: Qianwei Wang, Bowen Li, Zhanpeng Luo, Yifan Xu, Alexander Gray, Tom Silver, Sebastian Scherer, Katia Sycara, Yaqi Xie

Abstract: Long-horizon robotic tasks are hard due to continuous state-action spaces and sparse feedback. Symbolic world models help by decomposing tasks into discrete predicates that capture object properties and relations. Existing methods learn predicates either top-down, by prompting foundation models without data grounding, or bottom-up, from demonstrations without high-level priors. We introduce UniPre… ▽ More Long-horizon robotic tasks are hard due to continuous state-action spaces and sparse feedback. Symbolic world models help by decomposing tasks into discrete predicates that capture object properties and relations. Existing methods learn predicates either top-down, by prompting foundation models without data grounding, or bottom-up, from demonstrations without high-level priors. We introduce UniPred, a bilevel learning framework that unifies both. UniPred uses large language models (LLMs) to propose predicate effect distributions that supervise neural predicate learning from low-level data, while learned feedback iteratively refines the LLM hypotheses. Leveraging strong visual foundation model features, UniPred learns robust predicate classifiers in cluttered scenes. We further propose a predicate evaluation method that supports symbolic models beyond STRIPS assumptions. Across five simulated and one real-robot domains, UniPred achieves 2-4 times higher success rates than top-down methods and 3-4 times faster learning than bottom-up approaches, advancing scalable and flexible symbolic world modeling for robotics. △ Less

Submitted 19 December, 2025; originally announced December 2025.

Comments: 18 pages, 11 figures

Estimating the prevalence of LLM-assisted text in scholarly writing

Authors: Andrew Gray

Abstract: The use of large language models (LLMs) in scholarly publications has grown dramatically since the launch of ChatGPT in late 2022. This usage is often undisclosed, and it can be challenging for readers and reviewers to identify human written but LLM-revised or translated text, or predominantly LLM-generated text. Given the known quality and reliability issues connected with LLM-generated text, the… ▽ More The use of large language models (LLMs) in scholarly publications has grown dramatically since the launch of ChatGPT in late 2022. This usage is often undisclosed, and it can be challenging for readers and reviewers to identify human written but LLM-revised or translated text, or predominantly LLM-generated text. Given the known quality and reliability issues connected with LLM-generated text, their potential growth poses an increasing problem for research integrity, and for public trust in research. This study presents a simple and easily reproducible methodology to show the growth in the full text of published papers, across the full range of research, as indexed in the Dimensions database. It uses this to demonstrate that LLM tools are likely to have been involved in the production of more than 10% of all published papers in 2024, based on disproportionate use of specific indicative words, and draws together earlier studies to confirm that this is a plausible overall estimate. It then discusses the implications of this for the integrity of scholarly publishing, highlighting evidence that use of LLMs for text generation is still being concealed or downplayed by authors, and presents an argument that more comprehensive disclosure requirements are urgently required to address this. △ Less

Submitted 1 December, 2025; originally announced December 2025.

Comments: 19 pages, 3 figures

Correcting Prompt Dependence in LLM Benchmarks: A Bayesian Hierarchical Model with Embedding-Space Clustering

Authors: Mary Llewellyn, Isobel Thornton, James Bishop, Annie Gray

Abstract: LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assumptions that frequently do not hold in practice: (i) a sufficient number of evaluations are available for classical inference, and (ii) test prompts are independent. We propose a corrective Bayesian hierarchical model with embedding-space clustering that provides robust performance metrics in limited-data s… ▽ More LLM benchmarking metrics often misstate performance and uncertainty as they rely on two assumptions that frequently do not hold in practice: (i) a sufficient number of evaluations are available for classical inference, and (ii) test prompts are independent. We propose a corrective Bayesian hierarchical model with embedding-space clustering that provides robust performance metrics in limited-data settings while correcting for prompt dependence. We apply the approach to adversarial robustness benchmarks, showing consistent recovery of clustering structure, resulting in more reliable performance metrics, with 4-73% improvements to mean absolute errors and 40-450 unit improvements to expected log posterior densities. △ Less

Submitted 4 June, 2026; v1 submitted 7 October, 2025; originally announced October 2025.

Comments: Accepted to the 1st Workshop on Combining Theory and Benchmarks, CTB@ICML 2026, Seoul, South Korea

Redesigning GROMACS Halo Exchange: Improving Strong Scaling with GPU-initiated NVSHMEM

Authors: Mahesh Doijade, Andrey Alekseenko, Ania Brown, Alan Gray, Szilárd Páll

Abstract: Improving time-to-solution in molecular dynamics simulations often requires strong scaling due to fixed-sized problems. GROMACS is highly latency-sensitive, with peak iteration rates in the sub-millisecond, making scalability on heterogeneous supercomputers challenging. MPI's CPU-centric nature introduces additional latencies on GPU-resident applications' critical path, hindering GPU utilization a… ▽ More Improving time-to-solution in molecular dynamics simulations often requires strong scaling due to fixed-sized problems. GROMACS is highly latency-sensitive, with peak iteration rates in the sub-millisecond, making scalability on heterogeneous supercomputers challenging. MPI's CPU-centric nature introduces additional latencies on GPU-resident applications' critical path, hindering GPU utilization and scalability. To address these limitations, we present an NVSHMEM-based GPU kernel-initiated redesign of the GROMACS domain decomposition halo-exchange algorithm. Highly tuned GPU kernels fuse data packing and communication, leveraging hardware latency-hiding for fine-grained overlap. We employ kernel fusion across overlapped data forwarding communication phases and utilize the asynchronous copy engine over NVLink to optimize latency and bandwidth. Our GPU-resident formulation greatly increases communication-computation overlap, improving GROMACS strong scaling performance across NVLink by up to 1.5x (intra-node) and 2x (multi-node), and up to 1.3x multi-node over NVLink+InfiniBand. This demonstrates the profound benefits of GPU-initiated communication for strong-scaling a broad range of latency-sensitive applications. △ Less

Submitted 25 September, 2025; originally announced September 2025.

Comments: 17 pages, 8 figures, submitted to PAW-ATM Workshop, SC 2025

Multilinear and Linear Programs for Partially Identifiable Queries in Quasi-Markovian Structural Causal Models

Authors: João P. Arroyo, João G. Rodrigues, Daniel Lawand, Denis D. Mauá, Junkyu Lee, Radu Marinescu, Alex Gray, Eduardo R. Laurentino, Fabio G. Cozman

Abstract: We investigate partially identifiable queries in a class of causal models. We focus on acyclic Structural Causal Models that are quasi-Markovian (that is, each endogenous variable is connected with at most one exogenous confounder). We look into scenarios where endogenous variables are observed (and a distribution over them is known), while exogenous variables are not fully specified. This leads t… ▽ More We investigate partially identifiable queries in a class of causal models. We focus on acyclic Structural Causal Models that are quasi-Markovian (that is, each endogenous variable is connected with at most one exogenous confounder). We look into scenarios where endogenous variables are observed (and a distribution over them is known), while exogenous variables are not fully specified. This leads to a representation that is in essence a Bayesian network where the distribution of root variables is not uniquely determined. In such circumstances, it may not be possible to precisely compute a probability value of interest. We thus study the computation of tight probability bounds, a problem that has been solved by multilinear programming in general, and by linear programming when a single confounded component is intervened upon. We present a new algorithm to simplify the construction of such programs by exploiting input probabilities over endogenous variables. For scenarios with a single intervention, we apply column generation to compute a probability bound through a sequence of auxiliary linear integer programs, thus showing that a representation with polynomial cardinality for exogenous variables is possible. Experiments show column generation techniques to be superior to existing methods. △ Less

Submitted 2 September, 2025; originally announced September 2025.

Comments: Accepted at the Causal Abstractions and Representations (CAR) workshop of the 41st Conference on Uncertainty in Artificial Intelligence (UAI 2025)

Evaluating an Immersive Analytics Application at an Enterprise Business Intelligence Customer Conference

Authors: Matthew Brehmer, Ginger Gloystein, Bailiang Zhou, Abby Gray, Sruthi Pillai, Ben Medina, Vidya Setlur

Abstract: We reflect on an evaluation of an immersive analytics application (Tableau for visionOS) conducted at a large enterprise business intelligence (BI) conference. Conducting a study in such a context offered an opportunistic setting to gather diverse feedback. However, this setting also highlighted the challenge of evaluating usability while also assessing potential utility, as feedback straddled bet… ▽ More We reflect on an evaluation of an immersive analytics application (Tableau for visionOS) conducted at a large enterprise business intelligence (BI) conference. Conducting a study in such a context offered an opportunistic setting to gather diverse feedback. However, this setting also highlighted the challenge of evaluating usability while also assessing potential utility, as feedback straddled between the novelty of the experience and the practicality of the application in participants' analytical workflows. This formative evaluation with 22 participants allowed us to gather insights with respect to the usability of Tableau for visionOS, along with broader perspectives on the potential for head-mounted displays (HMDs) to promote new ways to engage with BI data. Our experience suggests a need for new evaluation considerations that integrate qualitative and quantitative measures and account for unique interaction patterns with 3D representations and interfaces accessible via an HMD. Overall, we contribute an enterprise perspective on evaluation methodologies for immersive analytics. △ Less

Submitted 20 August, 2025; originally announced August 2025.

Comments: To appear at the Human Factors in Immersive Analytics (HFIA) Workshop at IEEE VIS 2025

Transformers Learn Faster with Semantic Focus

Authors: Parikshit Ram, Kenneth L. Clarkson, Tim Klinger, Shashanka Ubaru, Alexander G. Gray

Abstract: Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of learnability and generalization. Empirically studying a range of attention mechanisms, we find that input-dependent sparse attention models appear to converge fas… ▽ More Various forms of sparse attention have been explored to mitigate the quadratic computational and memory cost of the attention mechanism in transformers. We study sparse transformers not through a lens of efficiency but rather in terms of learnability and generalization. Empirically studying a range of attention mechanisms, we find that input-dependent sparse attention models appear to converge faster and generalize better than standard attention models, while input-agnostic sparse attention models show no such benefits -- a phenomenon that is robust across architectural and optimization hyperparameter choices. This can be interpreted as demonstrating that concentrating a model's "semantic focus" with respect to the tokens currently being considered (in the form of input-dependent sparse attention) accelerates learning. We develop a theoretical characterization of the conditions that explain this behavior. We establish a connection between the stability of the standard softmax and the loss function's Lipschitz properties, then show how sparsity affects the stability of the softmax and the subsequent convergence and generalization guarantees resulting from the attention mechanism. This allows us to theoretically establish that input-agnostic sparse attention does not provide any benefits. We also characterize conditions when semantic focus (input-dependent sparse attention) can provide improved guarantees, and we validate that these conditions are in fact met in our empirical evaluations. △ Less

Submitted 18 June, 2025; v1 submitted 16 June, 2025; originally announced June 2025.

Open Challenges in Multi-Agent Security: Towards Secure Systems of Interacting AI Agents

Authors: Christian Schroeder de Witt, Klaudia Krawiecka, Igor Krawczuk, Ben Hagag, William L. Anderson, Peter Belcak, Ben Bucknall, Xiaohong Cai, Ayush Chopra, Doron Cohen, Ron F. Del Rosario, Andis Draguns, Annie Gray, Keren Katz, Vasilios Mavroudis, Jaron Mink, Sumeet Ramesh Motwani, Jonathan Petit, Leif-Sebastian Rembeck, Chandler Smith, John Sotiropoulos, Steven Young, Sarah Scheffler, Mary Llewellyn

Abstract: AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential for AI's task generalization but enable new threats like secret collusion and coordinated swarm attacks. Network effects can rapidly spread privacy breaches, di… ▽ More AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential for AI's task generalization but enable new threats like secret collusion and coordinated swarm attacks. Network effects can rapidly spread privacy breaches, disinformation, jailbreaks, and data poisoning, while multi-agent dispersion and stealth optimization help adversaries evade oversight - creating novel persistent threats at a systemic level. Despite their critical importance, these security challenges remain understudied, with research fragmented across disparate fields including AI security, multi-agent learning, complex systems, cybersecurity, game theory, distributed systems, and technical AI governance. We introduce multi-agent security, a new field dedicated to securing networks of AI agents against threats that emerge or amplify through their interactions - whether direct or indirect via shared environments - with each other, humans, and institutions, and characterise fundamental security-utility and security-security trade-offs across both distributed and decentralised settings. Our preliminary work (1) taxonomizes the threat landscape arising from interacting AI agents, (2) offers applications to multi-agent security for work across diffuse subfields, and (3) proposes a unified research agenda addressing open challenges in designing secure agent systems and interaction environments. By identifying these gaps, we aim to guide research in this critical area to unlock the socioeconomic potential of large-scale agent deployment, foster public trust, and mitigate national security risks in critical infrastructure and defense contexts. △ Less

Submitted 29 April, 2026; v1 submitted 4 May, 2025; originally announced May 2025.

Rendering Transparency to Ranking in Educational Assessment via Bayesian Comparative Judgement

Authors: Andy Gray, Alma Rahat, Stephen Lindsay, Jen Pearson, Tom Crick

Abstract: Ensuring transparency in educational assessment is increasingly critical, particularly post-pandemic, as demand grows for fairer and more reliable evaluation methods. Comparative Judgement (CJ) offers a promising alternative to traditional assessments, yet concerns remain about its perceived opacity. This paper examines how Bayesian Comparative Judgement (BCJ) enhances transparency by integrating… ▽ More Ensuring transparency in educational assessment is increasingly critical, particularly post-pandemic, as demand grows for fairer and more reliable evaluation methods. Comparative Judgement (CJ) offers a promising alternative to traditional assessments, yet concerns remain about its perceived opacity. This paper examines how Bayesian Comparative Judgement (BCJ) enhances transparency by integrating prior information into the judgement process, providing a structured, data-driven approach that improves interpretability and accountability. BCJ assigns probabilities to judgement outcomes, offering quantifiable measures of uncertainty and deeper insights into decision confidence. By systematically tracking how prior data and successive judgements inform final rankings, BCJ clarifies the assessment process and helps identify assessor disagreements. Multi-criteria BCJ extends this by evaluating multiple learning outcomes (LOs) independently, preserving the richness of CJ while producing transparent, granular rankings aligned with specific assessment goals. It also enables a holistic ranking derived from individual LOs, ensuring comprehensive evaluations without compromising detailed feedback. Using a real higher education dataset with professional markers in the UK, we demonstrate BCJ's quantitative rigour and ability to clarify ranking rationales. Through qualitative analysis and discussions with experienced CJ practitioners, we explore its effectiveness in contexts where transparency is crucial, such as high-stakes national assessments. We highlight the benefits and limitations of BCJ, offering insights into its real-world application across various educational settings. △ Less

Submitted 17 March, 2025; originally announced March 2025.

Bayesian Active Learning for Multi-Criteria Comparative Judgement in Educational Assessment

Authors: Andy Gray, Alma Rahat, Tom Crick, Stephen Lindsay

Abstract: Comparative Judgement (CJ) provides an alternative assessment approach by evaluating work holistically rather than breaking it into discrete criteria. This method leverages human ability to make nuanced comparisons, yielding more reliable and valid assessments. CJ aligns with real-world evaluations, where overall quality emerges from the interplay of various elements. However, rubrics remain widel… ▽ More Comparative Judgement (CJ) provides an alternative assessment approach by evaluating work holistically rather than breaking it into discrete criteria. This method leverages human ability to make nuanced comparisons, yielding more reliable and valid assessments. CJ aligns with real-world evaluations, where overall quality emerges from the interplay of various elements. However, rubrics remain widely used in education, offering structured criteria for grading and detailed feedback. This creates a gap between CJ's holistic ranking and the need for criterion-based performance breakdowns. This paper addresses this gap using a Bayesian approach. We build on Bayesian CJ (BCJ) by Gray et al., which directly models preferences instead of using likelihoods over total scores, allowing for expected ranks with uncertainty estimation. Their entropy-based active learning method selects the most informative pairwise comparisons for assessors. We extend BCJ to handle multiple independent learning outcome (LO) components, defined by a rubric, enabling both holistic and component-wise predictive rankings with uncertainty estimates. Additionally, we propose a method to aggregate entropies and identify the most informative comparison for assessors. Experiments on synthetic and real data demonstrate our method's effectiveness. Finally, we address a key limitation of BCJ, which is the inability to quantify assessor agreement. We show how to derive agreement levels, enhancing transparency in assessment. △ Less

Submitted 3 September, 2025; v1 submitted 1 March, 2025; originally announced March 2025.

Bilevel Learning for Bilevel Planning

Authors: Bowen Li, Tom Silver, Sebastian Scherer, Alexander Gray

Abstract: A robot that learns from demonstrations should not just imitate what it sees -- it should understand the high-level concepts that are being demonstrated and generalize them to new tasks. Bilevel planning is a hierarchical model-based approach where predicates (relational state abstractions) can be leveraged to achieve compositional generalization. However, previous bilevel planning approaches depe… ▽ More A robot that learns from demonstrations should not just imitate what it sees -- it should understand the high-level concepts that are being demonstrated and generalize them to new tasks. Bilevel planning is a hierarchical model-based approach where predicates (relational state abstractions) can be leveraged to achieve compositional generalization. However, previous bilevel planning approaches depend on predicates that are either hand-engineered or restricted to very simple forms, limiting their scalability to sophisticated, high-dimensional state spaces. To address this limitation, we present IVNTR, the first bilevel planning approach capable of learning neural predicates directly from demonstrations. Our key innovation is a neuro-symbolic bilevel learning framework that mirrors the structure of bilevel planning. In IVNTR, symbolic learning of the predicate "effects" and neural learning of the predicate "functions" alternate, with each providing guidance for the other. We evaluate IVNTR in six diverse robot planning domains, demonstrating its effectiveness in abstracting various continuous and high-dimensional states. While most existing approaches struggle to generalize (with <35% success rate), our IVNTR achieves an average of 77% success rate on unseen tasks. Additionally, we showcase IVNTR on a mobile manipulator, where it learns to perform real-world mobile manipulation tasks and generalizes to unseen test scenarios that feature new objects, new states, and longer task horizons. Our findings underscore the promise of learning and planning with abstractions as a path towards high-level generalization. △ Less

Submitted 11 May, 2025; v1 submitted 12 February, 2025; originally announced February 2025.

Comments: In Proceedings of Robotics, Science, and Systems (RSS 2025). See our website for details: https://jaraxxus-me.github.io/IVNTR/

Calibrated Physics-Informed Uncertainty Quantification

Authors: Vignesh Gopakumar, Ander Gray, Lorenzo Zanisi, Timothy Nunn, Daniel Giles, Matt J. Kusner, Stanislas Pamela, Marc Peter Deisenroth

Abstract: Simulating complex physical systems is crucial for understanding and predicting phenomena across diverse fields, such as fluid dynamics and heat transfer, as well as plasma physics and structural mechanics. Traditional approaches rely on solving partial differential equations (PDEs) using numerical methods, which are computationally expensive and often prohibitively slow for real-time applications… ▽ More Simulating complex physical systems is crucial for understanding and predicting phenomena across diverse fields, such as fluid dynamics and heat transfer, as well as plasma physics and structural mechanics. Traditional approaches rely on solving partial differential equations (PDEs) using numerical methods, which are computationally expensive and often prohibitively slow for real-time applications or large-scale simulations. Neural PDEs have emerged as efficient alternatives to these costly numerical solvers, offering significant computational speed-ups. However, their lack of robust uncertainty quantification (UQ) limits deployment in critical applications. We introduce a model-agnostic, physics-informed conformal prediction (CP) framework that provides guaranteed uncertainty estimates without requiring labelled data. By utilising a physics-based approach, we can quantify and calibrate the model's inconsistencies with the physics rather than the uncertainty arising from the data. Our approach utilises convolutional layers as finite-difference stencils and leverages physics residual errors as nonconformity scores, enabling data-free UQ with marginal and joint coverage guarantees across prediction domains for a range of complex PDEs. We further validate the efficacy of our method on neural PDE models for plasma modelling and shot design in fusion reactors. △ Less

Submitted 10 June, 2025; v1 submitted 6 February, 2025; originally announced February 2025.

Journal ref: ICML 2025

Guaranteed prediction sets for functional surrogate models

Authors: Ander Gray, Vignesh Gopakumar, Sylvain Rousseau, Sébastien Destercke

Abstract: We propose a method for obtaining statistically guaranteed prediction sets for functional machine learning methods: surrogate models which map between function spaces, motivated by the need to build reliable PDE emulators. The method constructs nested prediction sets on a low-dimensional representation (an SVD) of the surrogate model's error, and then maps these sets to the prediction space using… ▽ More We propose a method for obtaining statistically guaranteed prediction sets for functional machine learning methods: surrogate models which map between function spaces, motivated by the need to build reliable PDE emulators. The method constructs nested prediction sets on a low-dimensional representation (an SVD) of the surrogate model's error, and then maps these sets to the prediction space using set-propagation techniques. This results in prediction sets for functional surrogate models with conformal prediction coverage guarantees. We use zonotopes as basis of the set construction, which allow an exact linear propagation and are closed under Cartesian products, making them well-suited to this high-dimensional problem. The method is model agnostic and can thus be applied to complex Sci-ML models, including Neural Operators, but also in simpler settings. We also introduce a technique to capture the truncation error of the SVD, preserving the guarantees of the method. △ Less

Submitted 19 June, 2025; v1 submitted 30 January, 2025; originally announced January 2025.

Few-shot Policy (de)composition in Conversational Question Answering

Authors: Kyle Erwin, Guy Axelrod, Maria Chang, Achille Fokoue, Maxwell Crouse, Soham Dan, Tian Gao, Rosario Uceda-Sosa, Ndivhuwo Makondo, Naweed Khan, Alexander Gray

Abstract: The task of policy compliance detection (PCD) is to determine if a scenario is in compliance with respect to a set of written policies. In a conversational setting, the results of PCD can indicate if clarifying questions must be asked to determine compliance status. Existing approaches usually claim to have reasoning capabilities that are latent or require a large amount of annotated data. In this… ▽ More The task of policy compliance detection (PCD) is to determine if a scenario is in compliance with respect to a set of written policies. In a conversational setting, the results of PCD can indicate if clarifying questions must be asked to determine compliance status. Existing approaches usually claim to have reasoning capabilities that are latent or require a large amount of annotated data. In this work, we propose logical decomposition for policy compliance (LDPC): a neuro-symbolic framework to detect policy compliance using large language models (LLMs) in a few-shot setting. By selecting only a few exemplars alongside recently developed prompting techniques, we demonstrate that our approach soundly reasons about policy compliance conversations by extracting sub-questions to be answered, assigning truth values from contextual information, and explicitly producing a set of logic statements from the given policies. The formulation of explicit logic graphs can in turn help answer PCDrelated questions with increased transparency and explainability. We apply this approach to the popular PCD and conversational machine reading benchmark, ShARC, and show competitive performance with no task-specific finetuning. We also leverage the inherently interpretable architecture of LDPC to understand where errors occur, revealing ambiguities in the ShARC dataset and highlighting the challenges involved with reasoning for conversational question answering. △ Less

Submitted 20 January, 2025; originally announced January 2025.

Breaking through the classical Shannon entropy limit: A new frontier through logical semantics

Authors: Luis A. Lastras, Barry M. Trager, Jonathan Lenchner, Wojciech Szpankowski, Chai Wah Wu, Mark S. Squillante, Alexander Gray

Abstract: Information theory has provided foundations for the theories of several application areas critical for modern society, including communications, computer storage, and AI. A key aspect of Shannon's 1948 theory is a sharp lower bound on the number of bits needed to encode and communicate a string of symbols. When he introduced the theory, Shannon famously excluded any notion of semantics behind the… ▽ More Information theory has provided foundations for the theories of several application areas critical for modern society, including communications, computer storage, and AI. A key aspect of Shannon's 1948 theory is a sharp lower bound on the number of bits needed to encode and communicate a string of symbols. When he introduced the theory, Shannon famously excluded any notion of semantics behind the symbols being communicated. This semantics-free notion went on to have massive impact on communication and computing technologies, even as multiple proposals for reintroducing semantics in a theory of information were being made, notably one where Carnap and Bar-Hillel used logic and reasoning to capture semantics. In this paper we present, for the first time, a Shannon-style analysis of a communication system equipped with a deductive reasoning capability, implemented using logical inference. We use some of the most important techniques developed in information theory to demonstrate significant and sometimes surprising gains in communication efficiency availed to us through such capability, demonstrated also through practical codes. We thus argue that proposals for a semantic information theory should include the power of deductive reasoning to magnify the value of transmitted bits as we strive to fully unlock the inherent potential of semantics. △ Less

Submitted 31 December, 2024; originally announced January 2025.

LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation

Authors: Bowen Li, Zhaoyu Li, Qiwei Du, Jinqi Luo, Wenshan Wang, Yaqi Xie, Simon Stepputtis, Chen Wang, Katia P. Sycara, Pradeep Kumar Ravikumar, Alexander G. Gray, Xujie Si, Sebastian Scherer

Abstract: Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks with complex multi-agent interactions. Furthermore, they are usually constrained by fixed and simplistic logical rules over limited entities, making them… ▽ More Recent years have witnessed the rapid development of Neuro-Symbolic (NeSy) AI systems, which integrate symbolic reasoning into deep neural networks. However, most of the existing benchmarks for NeSy AI fail to provide long-horizon reasoning tasks with complex multi-agent interactions. Furthermore, they are usually constrained by fixed and simplistic logical rules over limited entities, making them far from real-world complexities. To address these crucial gaps, we introduce LogiCity, the first simulator based on customizable first-order logic (FOL) for an urban-like environment with multiple dynamic agents. LogiCity models diverse urban elements using semantic and spatial concepts, such as IsAmbulance(X) and IsClose(X, Y). These concepts are used to define FOL rules that govern the behavior of various agents. Since the concepts and rules are abstractions, they can be universally applied to cities with any agent compositions, facilitating the instantiation of diverse scenarios. Besides, a key feature of LogiCity is its support for user-configurable abstractions, enabling customizable simulation complexities for logical reasoning. To explore various aspects of NeSy AI, LogiCity introduces two tasks, one features long-horizon sequential decision-making, and the other focuses on one-step visual reasoning, varying in difficulty and agent behaviors. Our extensive evaluation reveals the advantage of NeSy frameworks in abstract reasoning. Moreover, we highlight the significant challenges of handling more complex abstractions in long-horizon multi-agent scenarios or under high-dimensional, imbalanced data. With its flexible design, various features, and newly raised challenges, we believe LogiCity represents a pivotal step forward in advancing the next generation of NeSy AI. All the code and data are open-sourced at our website: https://jaraxxus-me.github.io/LogiCity/ △ Less

Submitted 3 April, 2025; v1 submitted 1 November, 2024; originally announced November 2024.

Comments: 25 pages, 8 figures, In Advances in Neural Information Processing Systems (NeurIPS) 37 D&B Track (2024): 69840-69864

Journal ref: Advances in Neural Information Processing Systems, 37, 69840-69864 (2024)

Neural Reasoning Networks: Efficient Interpretable Neural Networks With Automatic Textual Explanations

Authors: Stephen Carrow, Kyle Harper Erwin, Olga Vilenskaia, Parikshit Ram, Tim Klinger, Naweed Aghmad Khan, Ndivhuwo Makondo, Alexander Gray

Abstract: Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is necessary to ensure fairness, safety, and legal compliance. In this paper we consider one class of such tasks, tabular dataset classification, and propose a nov… ▽ More Recent advances in machine learning have led to a surge in adoption of neural networks for various tasks, but lack of interpretability remains an issue for many others in which an understanding of the features influencing the prediction is necessary to ensure fairness, safety, and legal compliance. In this paper we consider one class of such tasks, tabular dataset classification, and propose a novel neuro-symbolic architecture, Neural Reasoning Networks (NRN), that is scalable and generates logically sound textual explanations for its predictions. NRNs are connected layers of logical neurons which implement a form of real valued logic. A training algorithm (R-NRN) learns the weights of the network as usual using gradient descent optimization with backprop, but also learns the network structure itself using a bandit-based optimization. Both are implemented in an extension to PyTorch (https://github.com/IBM/torchlogic) that takes full advantage of GPU scaling and batched training. Evaluation on a diverse set of 22 open-source datasets for tabular classification demonstrates performance (measured by ROC AUC) which improves over multi-layer perceptron (MLP) and is statistically similar to other state-of-the-art approaches such as Random Forest, XGBoost and Gradient Boosted Trees, while offering 43% faster training and a more than 2 orders of magnitude reduction in the number of parameters required, on average. Furthermore, R-NRN explanations are shorter than the compared approaches while producing more accurate feature importance scores. △ Less

Submitted 10 October, 2024; originally announced October 2024.

ACM Class: I.2.6; I.5.1

Heterogeneous computing in a strongly-connected CPU-GPU environment: fast multiple time-evolution equation-based modeling accelerated using data-driven approach

Authors: Tsuyoshi Ichimura, Kohei Fujita, Muneo Hori, Lalith Maddegedara, Jack Wells, Alan Gray, Ian Karlin, John Linford

Abstract: We propose a CPU-GPU heterogeneous computing method for solving time-evolution partial differential equation problems many times with guaranteed accuracy, in short time-to-solution and low energy-to-solution. On a single-GH200 node, the proposed method improved the computation speed by 86.4 and 8.67 times compared to the conventional method run only on CPU and only on GPU, respectively. Furthermor… ▽ More We propose a CPU-GPU heterogeneous computing method for solving time-evolution partial differential equation problems many times with guaranteed accuracy, in short time-to-solution and low energy-to-solution. On a single-GH200 node, the proposed method improved the computation speed by 86.4 and 8.67 times compared to the conventional method run only on CPU and only on GPU, respectively. Furthermore, the energy-to-solution was reduced by 32.2-fold (from 9944 J to 309 J) and 7.01-fold (from 2163 J to 309 J) when compared to using only the CPU and GPU, respectively. Using the proposed method on the Alps supercomputer, a 51.6-fold and 6.98-fold speedup was attained when compared to using only the CPU and GPU, respectively, and a high weak scaling efficiency of 94.3% was obtained up to 1,920 compute nodes. These implementations were realized using directive-based parallel programming models while enabling portability, indicating that directives are highly effective in analyses in heterogeneous computing environments. △ Less

Submitted 30 September, 2024; originally announced September 2024.

Comments: 22 pages, 5 figures, accepted for Eleventh Workshop on Accelerator Programming and Directives (WACCPD 2024)

Uncertainty Quantification of Surrogate Models using Conformal Prediction

Authors: Vignesh Gopakumar, Ander Gray, Joel Oskarsson, Lorenzo Zanisi, Daniel Giles, Matt J. Kusner, Stanislas Pamela, Marc Peter Deisenroth

Abstract: Data-driven surrogate models offer quick approximations to complex numerical and experimental systems but typically lack uncertainty quantification, limiting their reliability in safety-critical applications. While Bayesian methods provide uncertainty estimates, they offer no statistical guarantees and struggle with high-dimensional spatio-temporal problems due to computational costs. We present a… ▽ More Data-driven surrogate models offer quick approximations to complex numerical and experimental systems but typically lack uncertainty quantification, limiting their reliability in safety-critical applications. While Bayesian methods provide uncertainty estimates, they offer no statistical guarantees and struggle with high-dimensional spatio-temporal problems due to computational costs. We present a conformal prediction (CP) framework that provides statistically guaranteed marginal coverage for surrogate models in a model-agnostic manner with near-zero computational cost. Our approach handles high-dimensional spatio-temporal outputs by performing cell-wise calibration while preserving the tensorial structure of predictions. Through extensive empirical evaluation across diverse applications including fluid dynamics, magnetohydrodynamics, weather forecasting, and fusion diagnostics, we demonstrate that CP achieves empirical coverage with valid error bars regardless of model architecture, training regime, or output dimensionality. We evaluate three nonconformity scores (conformalised quantile regression, absolute error residual, and standard deviation) for both deterministic and probabilistic models, showing that guaranteed coverage holds even for out-of-distribution predictions where models are deployed on physics regimes different from training data. Calibration requires only seconds to minutes on standard hardware. The framework enables rigorous validation of pre-trained surrogate models for downstream applications without retraining. While CP provides marginal rather than conditional coverage and assumes exchangeability between calibration and test data, our method circumvents the curse of dimensionality inherent in traditional uncertainty quantification approaches, offering a practical tool for trustworthy deployment of machine learning in physical sciences. △ Less

Submitted 5 January, 2026; v1 submitted 19 August, 2024; originally announced August 2024.

Evaluating Ensemble Methods for News Recommender Systems

Authors: Alexander Gray, Noorhan Abbas

Abstract: News recommendation is crucial for facilitating individuals' access to articles, particularly amid the increasingly digital landscape of news consumption. Consequently, extensive research is dedicated to News Recommender Systems (NRS) with increasingly sophisticated algorithms. Despite this sustained scholarly inquiry, there exists a notable research gap regarding the potential synergy achievable… ▽ More News recommendation is crucial for facilitating individuals' access to articles, particularly amid the increasingly digital landscape of news consumption. Consequently, extensive research is dedicated to News Recommender Systems (NRS) with increasingly sophisticated algorithms. Despite this sustained scholarly inquiry, there exists a notable research gap regarding the potential synergy achievable by amalgamating these algorithms to yield superior outcomes. This paper endeavours to address this gap by demonstrating how ensemble methods can be used to combine many diverse state-of-the-art algorithms to achieve superior results on the Microsoft News dataset (MIND). Additionally, we identify scenarios where ensemble methods fail to improve results and offer explanations for this occurrence. Our findings demonstrate that a combination of NRS algorithms can outperform individual algorithms, provided that the base learners are sufficiently diverse, with improvements of up to 5\% observed for an ensemble consisting of a content-based BERT approach and the collaborative filtering LSTUR algorithm. Additionally, our results demonstrate the absence of any improvement when combining insufficiently distinct methods. These findings provide insight into successful approaches of ensemble methods in NRS and advocates for the development of better systems through appropriate ensemble solutions. △ Less

Submitted 23 June, 2024; originally announced June 2024.

Valid Error Bars for Neural Weather Models using Conformal Prediction

Authors: Vignesh Gopakumar, Joel Oskarrson, Ander Gray, Lorenzo Zanisi, Stanislas Pamela, Daniel Giles, Matt Kusner, Marc Deisenroth

Abstract: Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This limits the trust in the model and the usefulness of the forecasts. In this work we construct and formalise a conformal prediction framework as a post-pro… ▽ More Neural weather models have shown immense potential as inexpensive and accurate alternatives to physics-based models. However, most models trained to perform weather forecasting do not quantify the uncertainty associated with their forecasts. This limits the trust in the model and the usefulness of the forecasts. In this work we construct and formalise a conformal prediction framework as a post-processing method for estimating this uncertainty. The method is model-agnostic and gives calibrated error bounds for all variables, lead times and spatial locations. No modifications are required to the model and the computational cost is negligible compared to model training. We demonstrate the usefulness of the conformal prediction framework on a limited area neural weather model for the Nordic region. We further explore the advantages of the framework for deterministic and probabilistic models. △ Less

Submitted 20 June, 2024; originally announced June 2024.

What makes Models Compositional? A Theoretical View: With Supplement

Authors: Parikshit Ram, Tim Klinger, Alexander G. Gray

Abstract: Compositionality is thought to be a key component of language, and various compositional benchmarks have been developed to empirically probe the compositional generalization of existing sequence processing models. These benchmarks often highlight failures of existing models, but it is not clear why these models fail in this way. In this paper, we seek to theoretically understand the role the compo… ▽ More Compositionality is thought to be a key component of language, and various compositional benchmarks have been developed to empirically probe the compositional generalization of existing sequence processing models. These benchmarks often highlight failures of existing models, but it is not clear why these models fail in this way. In this paper, we seek to theoretically understand the role the compositional structure of the models plays in these failures and how this structure relates to their expressivity and sample complexity. We propose a general neuro-symbolic definition of compositional functions and their compositional complexity. We then show how various existing general and special purpose sequence processing models (such as recurrent, convolution and attention-based ones) fit this definition and use it to analyze their compositional complexity. Finally, we provide theoretical guarantees for the expressivity and systematic generalization of compositional models that explicitly depend on our proposed definition and highlighting factors which drive poor empirical performance. △ Less

Submitted 2 May, 2024; originally announced May 2024.

Comments: Extended version of the original IJCAI 2024 paper with detailed supplementary materials (27 pages, 7 figures)

ChatGPT "contamination": estimating the prevalence of LLMs in the scholarly literature

Authors: Andrew Gray

Abstract: The use of ChatGPT and similar Large Language Model (LLM) tools in scholarly communication and academic publishing has been widely discussed since they became easily accessible to a general audience in late 2022. This study uses keywords known to be disproportionately present in LLM-generated text to provide an overall estimate for the prevalence of LLM-assisted writing in the scholarly literature… ▽ More The use of ChatGPT and similar Large Language Model (LLM) tools in scholarly communication and academic publishing has been widely discussed since they became easily accessible to a general audience in late 2022. This study uses keywords known to be disproportionately present in LLM-generated text to provide an overall estimate for the prevalence of LLM-assisted writing in the scholarly literature. For the publishing year 2023, it is found that several of those keywords show a distinctive and disproportionate increase in their prevalence, individually and in combination. It is estimated that at least 60,000 papers (slightly over 1% of all articles) were LLM-assisted, though this number could be extended and refined by analysis of other characteristics of the papers or by identification of further indicative keywords. △ Less

Submitted 25 March, 2024; originally announced March 2024.

Comments: 12 pages, 6 figures

A Neuro-Symbolic Approach to Multi-Agent RL for Interpretability and Probabilistic Decision Making

Authors: Chitra Subramanian, Miao Liu, Naweed Khan, Jonathan Lenchner, Aporva Amarnath, Sarathkrishna Swaminathan, Ryan Riegel, Alexander Gray

Abstract: Multi-agent reinforcement learning (MARL) is well-suited for runtime decision-making in optimizing the performance of systems where multiple agents coexist and compete for shared resources. However, applying common deep learning-based MARL solutions to real-world problems suffers from issues of interpretability, sample efficiency, partial observability, etc. To address these challenges, we present… ▽ More Multi-agent reinforcement learning (MARL) is well-suited for runtime decision-making in optimizing the performance of systems where multiple agents coexist and compete for shared resources. However, applying common deep learning-based MARL solutions to real-world problems suffers from issues of interpretability, sample efficiency, partial observability, etc. To address these challenges, we present an event-driven formulation, where decision-making is handled by distributed co-operative MARL agents using neuro-symbolic methods. The recently introduced neuro-symbolic Logical Neural Networks (LNN) framework serves as a function approximator for the RL, to train a rules-based policy that is both logical and interpretable by construction. To enable decision-making under uncertainty and partial observability, we developed a novel probabilistic neuro-symbolic framework, Probabilistic Logical Neural Networks (PLNN), which combines the capabilities of logical reasoning with probabilistic graphical models. In PLNN, the upward/downward inference strategy, inherited from LNN, is coupled with belief bounds by setting the activation function for the logical operator associated with each neural network node to a probability-respecting generalization of the Fréchet inequalities. These PLNN nodes form the unifying element that combines probabilistic logic and Bayes Nets, permitting inference for variables with unobserved states. We demonstrate our contributions by addressing key MARL challenges for power sharing in a system-on-chip application. △ Less

Submitted 20 February, 2024; originally announced February 2024.

ACM Class: I.2.6

Plasma Surrogate Modelling using Fourier Neural Operators

Authors: Vignesh Gopakumar, Stanislas Pamela, Lorenzo Zanisi, Zongyi Li, Ander Gray, Daniel Brennand, Nitesh Bhatia, Gregory Stathopoulos, Matt Kusner, Marc Peter Deisenroth, Anima Anandkumar, JOREK Team, MAST Team

Abstract: Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. Capabilities in forecasting the spatio-temporal evolution of plasma rapidly and accurately allow us to quickly iterate over design and control strategies on current Tokamak devices and future reactors. Modelling plasma evolution using numerical solvers is often expensive, consuming many hou… ▽ More Predicting plasma evolution within a Tokamak reactor is crucial to realizing the goal of sustainable fusion. Capabilities in forecasting the spatio-temporal evolution of plasma rapidly and accurately allow us to quickly iterate over design and control strategies on current Tokamak devices and future reactors. Modelling plasma evolution using numerical solvers is often expensive, consuming many hours on supercomputers, and hence, we need alternative inexpensive surrogate models. We demonstrate accurate predictions of plasma evolution both in simulation and experimental domains using deep learning-based surrogate modelling tools, viz., Fourier Neural Operators (FNO). We show that FNO has a speedup of six orders of magnitude over traditional solvers in predicting the plasma dynamics simulated from magnetohydrodynamic models, while maintaining a high accuracy (MSE in the normalised domain $\approx$ $10^{-5}$). Our modified version of the FNO is capable of solving multi-variable Partial Differential Equations (PDE), and can capture the dependence among the different variables in a single model. FNOs can also predict plasma evolution on real-world experimental data observed by the cameras positioned within the MAST Tokamak, i.e., cameras looking across the central solenoid and the divertor in the Tokamak. We show that FNOs are able to accurately forecast the evolution of plasma and have the potential to be deployed for real-time monitoring. We also illustrate their capability in forecasting the plasma shape, the locations of interactions of the plasma with the central solenoid and the divertor for the full (available) duration of the plasma shot within MAST. The FNO offers a viable alternative for surrogate modelling as it is quick to train and infer, and requires fewer data points, while being able to do zero-shot super-resolution and getting high-fidelity solutions. △ Less

Submitted 18 June, 2024; v1 submitted 10 November, 2023; originally announced November 2023.

Journal ref: Nucl. Fusion 64 056025 (2024)

Compositional Program Generation for Few-Shot Systematic Generalization

Authors: Tim Klinger, Luke Liu, Soham Dan, Maxwell Crouse, Parikshit Ram, Alexander Gray

Abstract: Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples. Neural machine learning models, including the now ubiquitous Transformers, struggle to generalize in this way, and typically require thousands of examples of a concept during training in order to generalize meaningfully. This difference in ability between humans and artificia… ▽ More Compositional generalization is a key ability of humans that enables us to learn new concepts from only a handful examples. Neural machine learning models, including the now ubiquitous Transformers, struggle to generalize in this way, and typically require thousands of examples of a concept during training in order to generalize meaningfully. This difference in ability between humans and artificial neural architectures, motivates this study on a neuro-symbolic architecture called the Compositional Program Generator (CPG). CPG has three key features: \textit{modularity}, \textit{composition}, and \textit{abstraction}, in the form of grammar rules, that enable it to generalize both systematically to new concepts in a few-shot manner, as well as productively by length on various sequence-to-sequence language tasks. For each input, CPG uses a grammar of the input language and a parser to generate a parse in which each grammar rule is assigned its own unique semantic module, a probabilistic copy or substitution program. Instances with the same parse are always processed with the same composed modules, while those with different parses may be processed with different modules. CPG learns parameters for the modules and is able to learn the semantics for new rules and types incrementally, without forgetting or retraining on rules it's already seen. It achieves perfect generalization on both the SCAN and COGS benchmarks using just 14 examples for SCAN and 22 examples for COGS -- state-of-the-art accuracy with a 1000x improvement in sample efficiency. △ Less

Submitted 18 January, 2024; v1 submitted 28 September, 2023; originally announced September 2023.

Comments: 7 pages of text with 1 page of references

A Bayesian Active Learning Approach to Comparative Judgement

Authors: Andy Gray, Alma Rahat, Tom Crick, Stephen Lindsay

Abstract: Assessment is a crucial part of education. Traditional marking is a source of inconsistencies and unconscious bias, placing a high cognitive load on the assessors. An approach to address these issues is comparative judgement (CJ). In CJ, the assessor is presented with a pair of items and is asked to select the better one. Following a series of comparisons, a rank is derived using a ranking model,… ▽ More Assessment is a crucial part of education. Traditional marking is a source of inconsistencies and unconscious bias, placing a high cognitive load on the assessors. An approach to address these issues is comparative judgement (CJ). In CJ, the assessor is presented with a pair of items and is asked to select the better one. Following a series of comparisons, a rank is derived using a ranking model, for example, the BTM, based on the results. While CJ is considered a reliable method for marking, there are concerns around transparency, and the ideal number of pairwise comparisons to generate a reliable estimation of the rank order is not known. Additionally, there have been attempts to generate a method of selecting pairs that should be compared next in an informative manner, but some existing methods are known to have created their own bias within results inflating the reliability metric used. As a result, a random selection approach is usually deployed. We propose a novel Bayesian approach to CJ (BCJ) for determining the ranks of compared items alongside a new way to select the pairs to present to the marker(s) using active learning (AL), addressing the key shortcomings of traditional CJ. Furthermore, we demonstrate how the entire approach may provide transparency by providing the user insights into how it is making its decisions and, at the same time, being more efficient. Results from our experiments confirm that the proposed BCJ combined with entropy-driven AL pair-selection method is superior to other alternatives. We also find that the more comparisons done, the more accurate BCJ becomes, which solves the issue the current method has of the model deteriorating if too many comparisons are performed. As our approach can generate the complete predicted rank distribution for an item, we also show how this can be utilised in devising a predicted grade, guided by the assessor. △ Less

Submitted 25 August, 2023; originally announced August 2023.

Comments: 16 pages

Learning Symbolic Rules over Abstract Meaning Representations for Textual Reinforcement Learning

Authors: Subhajit Chaudhury, Sarathkrishna Swaminathan, Daiki Kimura, Prithviraj Sen, Keerthiram Murugesan, Rosario Uceda-Sosa, Michiaki Tatsubori, Achille Fokoue, Pavan Kapanipathi, Asim Munawar, Alexander Gray

Abstract: Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. Th… ▽ More Text-based reinforcement learning agents have predominantly been neural network-based models with embeddings-based representation, learning uninterpretable policies that often do not generalize well to unseen games. On the other hand, neuro-symbolic methods, specifically those that leverage an intermediate formal representation, are gaining significant attention in language understanding tasks. This is because of their advantages ranging from inherent interpretability, the lesser requirement of training data, and being generalizable in scenarios with unseen data. Therefore, in this paper, we propose a modular, NEuro-Symbolic Textual Agent (NESTA) that combines a generic semantic parser with a rule induction system to learn abstract interpretable rules as policies. Our experiments on established text-based game benchmarks show that the proposed NESTA method outperforms deep reinforcement learning-based techniques by achieving better generalization to unseen test games and learning from fewer training interactions. △ Less

Submitted 5 July, 2023; originally announced July 2023.

Comments: ACL 2023

A Comparison of Neuroelectrophysiology Databases

Authors: Priyanka Subash, Alex Gray, Misque Boswell, Samantha L. Cohen, Rachael Garner, Sana Salehi, Calvary Fisher, Samuel Hobel, Satrajit Ghosh, Yaroslav Halchenko, Benjamin Dichter, Russell A. Poldrack, Chris Markiewicz, Dora Hermes, Arnaud Delorme, Scott Makeig, Brendan Behan, Alana Sparks, Stephen R Arnott, Zhengjia Wang, John Magnotti, Michael S. Beauchamp, Nader Pouratian, Arthur W. Toga, Dominique Duncan

Abstract: As data sharing has become more prevalent, three pillars - archives, standards, and analysis tools - have emerged as critical components in facilitating effective data sharing and collaboration. This paper compares four freely available intracranial neuroelectrophysiology data repositories: Data Archive for the BRAIN Initiative (DABI), Distributed Archives for Neurophysiology Data Integration (DAN… ▽ More As data sharing has become more prevalent, three pillars - archives, standards, and analysis tools - have emerged as critical components in facilitating effective data sharing and collaboration. This paper compares four freely available intracranial neuroelectrophysiology data repositories: Data Archive for the BRAIN Initiative (DABI), Distributed Archives for Neurophysiology Data Integration (DANDI), OpenNeuro, and Brain-CODE. The aim of this review is to describe archives that provide researchers with tools to store, share, and reanalyze both human and non-human neurophysiology data based on criteria that are of interest to the neuroscientific community. The Brain Imaging Data Structure (BIDS) and Neurodata Without Borders (NWB) are utilized by these archives to make data more accessible to researchers by implementing a common standard. As the necessity for integrating large-scale analysis into data repository platforms continues to grow within the neuroscientific community, this article will highlight the various analytical and customizable tools developed within the chosen archives that may advance the field of neuroinformatics. △ Less

Submitted 30 August, 2023; v1 submitted 26 June, 2023; originally announced June 2023.

Comments: 22 pages, 6 figures, 5 tables

Can GPT-4 Support Analysis of Textual Data in Tasks Requiring Highly Specialized Domain Expertise?

Authors: Jaromir Savelka, Kevin D. Ashley, Morgan A Gray, Hannes Westermann, Huihui Xu

Abstract: We evaluated the capability of generative pre-trained transformers~(GPT-4) in analysis of textual data in tasks that require highly specialized domain expertise. Specifically, we focused on the task of analyzing court opinions to interpret legal concepts. We found that GPT-4, prompted with annotation guidelines, performs on par with well-trained law student annotators. We observed that, with a rel… ▽ More We evaluated the capability of generative pre-trained transformers~(GPT-4) in analysis of textual data in tasks that require highly specialized domain expertise. Specifically, we focused on the task of analyzing court opinions to interpret legal concepts. We found that GPT-4, prompted with annotation guidelines, performs on par with well-trained law student annotators. We observed that, with a relatively minor decrease in performance, GPT-4 can perform batch predictions leading to significant cost reductions. However, employing chain-of-thought prompting did not lead to noticeably improved performance on this task. Further, we demonstrated how to analyze GPT-4's predictions to identify and mitigate deficiencies in annotation guidelines, and subsequently improve the performance of the model. Finally, we observed that the model is quite brittle, as small formatting related changes in the prompt had a high impact on the predictions. These findings can be leveraged by researchers and practitioners who engage in semantic/pragmatic annotations of texts in the context of the tasks requiring highly specialized domain expertise. △ Less

Submitted 24 June, 2023; originally announced June 2023.

Journal ref: ITiCSE 2023: Proceedings of the 2023 Conference on Innovation and Technology in Computer Science Education V. 1. June 2023. Pages 117 - 123

MISMATCH: Fine-grained Evaluation of Machine-generated Text with Mismatch Error Types

Authors: Keerthiram Murugesan, Sarathkrishna Swaminathan, Soham Dan, Subhajit Chaudhury, Chulaka Gunasekara, Maxwell Crouse, Diwakar Mahajan, Ibrahim Abdelaziz, Achille Fokoue, Pavan Kapanipathi, Salim Roukos, Alexander Gray

Abstract: With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal attention. Most recent works focus either on task-specific evaluation metrics or study the properties of machine-generated text captured by the existing metrics. In this work, we propose a new evaluation scheme to model huma… ▽ More With the growing interest in large language models, the need for evaluating the quality of machine text compared to reference (typically human-generated) text has become focal attention. Most recent works focus either on task-specific evaluation metrics or study the properties of machine-generated text captured by the existing metrics. In this work, we propose a new evaluation scheme to model human judgments in 7 NLP tasks, based on the fine-grained mismatches between a pair of texts. Inspired by the recent efforts in several NLP tasks for fine-grained evaluation, we introduce a set of 13 mismatch error types such as spatial/geographic errors, entity errors, etc, to guide the model for better prediction of human judgments. We propose a neural framework for evaluating machine texts that uses these mismatch error types as auxiliary tasks and re-purposes the existing single-number evaluation metrics as additional scalar features, in addition to textual features extracted from the machine and reference texts. Our experiments reveal key insights about the existing metrics via the mismatch errors. We show that the mismatch errors between the sentence pairs on the held-out datasets from 7 NLP tasks align well with the human evaluation. △ Less

Submitted 17 June, 2023; originally announced June 2023.

Comments: Accepted at ACL 2023 (ACL Findings Long)

Explaining Legal Concepts with Augmented Large Language Models (GPT-4)

Authors: Jaromir Savelka, Kevin D. Ashley, Morgan A. Gray, Hannes Westermann, Huihui Xu

Abstract: Interpreting the meaning of legal open-textured terms is a key task of legal professionals. An important source for this interpretation is how the term was applied in previous court cases. In this paper, we evaluate the performance of GPT-4 in generating factually accurate, clear and relevant explanations of terms in legislation. We compare the performance of a baseline setup, where GPT-4 is direc… ▽ More Interpreting the meaning of legal open-textured terms is a key task of legal professionals. An important source for this interpretation is how the term was applied in previous court cases. In this paper, we evaluate the performance of GPT-4 in generating factually accurate, clear and relevant explanations of terms in legislation. We compare the performance of a baseline setup, where GPT-4 is directly asked to explain a legal term, to an augmented approach, where a legal information retrieval module is used to provide relevant context to the model, in the form of sentences from case law. We found that the direct application of GPT-4 yields explanations that appear to be of very high quality on their surface. However, detailed analysis uncovered limitations in terms of the factual accuracy of the explanations. Further, we found that the augmentation leads to improved quality, and appears to eliminate the issue of hallucination, where models invent incorrect statements. These findings open the door to the building of systems that can autonomously retrieve relevant sentences from case law and condense them into a useful explanation for legal scholars, educators or practicing lawyers alike. △ Less

Submitted 22 June, 2023; v1 submitted 15 June, 2023; originally announced June 2023.

Scalable Learning of Latent Language Structure With Logical Offline Cycle Consistency

Authors: Maxwell Crouse, Ramon Astudillo, Tahira Naseem, Subhajit Chaudhury, Pavan Kapanipathi, Salim Roukos, Alexander Gray

Abstract: We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as a form of self-learning where the semantic parser being trained is used to generate annotations for unlabeled text that are then used as new supervision. To increase the quality of annotations, our method utilizes a coun… ▽ More We introduce Logical Offline Cycle Consistency Optimization (LOCCO), a scalable, semi-supervised method for training a neural semantic parser. Conceptually, LOCCO can be viewed as a form of self-learning where the semantic parser being trained is used to generate annotations for unlabeled text that are then used as new supervision. To increase the quality of annotations, our method utilizes a count-based prior over valid formal meaning representations and a cycle-consistency score produced by a neural text generation model as additional signals. Both the prior and semantic parser are updated in an alternate fashion from full passes over the training data, which can be seen as approximating the marginalization of latent structures through stochastic variational inference. The use of a count-based prior, frozen text generation model, and offline annotation process yields an approach with negligible complexity and latency increases as compared to conventional self-learning. As an added bonus, the annotations produced by LOCCO can be trivially repurposed to train a neural text generation model. We demonstrate the utility of LOCCO on the well-known WebNLG benchmark where we obtain an improvement of 2 points against a self-learning parser under equivalent conditions, an improvement of 1.3 points against the previous state-of-the-art parser, and competitive text generation performance in terms of BLEU score. △ Less

Submitted 31 May, 2023; originally announced May 2023.

Hierarchical clustering with dot products recovers hidden tree structure

Authors: Annie Gray, Alexander Modell, Patrick Rubin-Delanchy, Nick Whiteley

Abstract: In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure. We recommend a simple variant of the standard algorithm, in which clusters are merged by maximum average dot product and not, for example, by minimum distance or within-cluster variance. We demonstrate that the tree output by this algorithm provides a… ▽ More In this paper we offer a new perspective on the well established agglomerative clustering algorithm, focusing on recovery of hierarchical structure. We recommend a simple variant of the standard algorithm, in which clusters are merged by maximum average dot product and not, for example, by minimum distance or within-cluster variance. We demonstrate that the tree output by this algorithm provides a bona fide estimate of generative hierarchical structure in data, under a generic probabilistic graphical model. The key technical innovations are to understand how hierarchical information in this model translates into tree geometry which can be recovered from data, and to characterise the benefits of simultaneously growing sample size and data dimension. We demonstrate superior tree recovery performance with real data over existing approaches such as UPGMA, Ward's method, and HDBSCAN. △ Less

Submitted 1 March, 2024; v1 submitted 24 May, 2023; originally announced May 2023.

Towards a Unification of Logic and Information Theory

Authors: Luis A. Lastras, Barry Trager, Jonathan Lenchner, Wojtek Szpankowski, Chai Wah Wu, Mark Squillante, Ron Fagin, Alex Gray

Abstract: Today, the vast majority of the world's digital information is represented using the fundamental assumption, introduced by Claude Shannon in 1948, that ``...the semantic aspects of communication are irrelevant to the engineering problem (of the design of communication systems)...''. Consider, nonetheless, the observation that we often combine a message with other information in order to deduce new… ▽ More Today, the vast majority of the world's digital information is represented using the fundamental assumption, introduced by Claude Shannon in 1948, that ``...the semantic aspects of communication are irrelevant to the engineering problem (of the design of communication systems)...''. Consider, nonetheless, the observation that we often combine a message with other information in order to deduce new facts, thereby expanding the value of such a message. It is noteworthy that to-date, no rigorous theory of communication has been put forth which postulates the existence of deductive capabilities on the receiver's side. The purpose of this paper is to present such a theory. We formally model such deductive capabilities using logic reasoning, and present a rigorous theory which covers the following generic scenario: Alice and Bob each have knowledge of some logic sentence, and they wish to communicate as efficiently as possible with the shared goal that, following their communication, Bob should be able to deduce a particular logic sentence that Alice knows to be true, but that Bob currently cannot prove. Many variants of this general setup are considered in this article; in all cases we are able to provide sharp upper and lower bounds. Our contribution includes the identification of the most fundamental requirements that we place on a logic and associated logical language for all of our results to apply. Practical algorithms that are in some cases asymptotically optimal are provided, and we illustrate the potential practical value of the design of communication systems that incorporate the assumption of deductive capabilities at the receiver using experimental results that suggest significant possible gains compared to classical systems. △ Less

Submitted 12 September, 2025; v1 submitted 25 January, 2023; originally announced January 2023.

Toward Theoretical Guidance for Two Common Questions in Practical Cross-Validation based Hyperparameter Selection

Authors: Parikshit Ram, Alexander G. Gray, Horst C. Samulowitz, Gregory Bramble

Abstract: We show, to our knowledge, the first theoretical treatments of two common questions in cross-validation based hyperparameter selection: (1) After selecting the best hyperparameter using a held-out set, we train the final model using {\em all} of the training data -- since this may or may not improve future generalization error, should one do this? (2) During optimization such as via SGD (stochasti… ▽ More We show, to our knowledge, the first theoretical treatments of two common questions in cross-validation based hyperparameter selection: (1) After selecting the best hyperparameter using a held-out set, we train the final model using {\em all} of the training data -- since this may or may not improve future generalization error, should one do this? (2) During optimization such as via SGD (stochastic gradient descent), we must set the optimization tolerance $ρ$ -- since it trades off predictive accuracy with computation cost, how should one set it? Toward these problems, we introduce the {\em hold-in risk} (the error due to not using the whole training data), and the {\em model class mis-specification risk} (the error due to having chosen the wrong model class) in a theoretical view which is simple, general, and suggests heuristics that can be used when faced with a dataset instance. In proof-of-concept studies in synthetic data where theoretical quantities can be controlled, we show that these heuristics can, respectively, (1) always perform at least as well as always performing retraining or never performing retraining, (2) either improve performance or reduce computational overhead by $2\times$ with no loss in predictive performance. △ Less

Submitted 12 January, 2023; originally announced January 2023.

Comments: Extended version of the paper appearing at the SIAM International Conference on Data Mining 2023 (SDM23)

Statistical exploration of the Manifold Hypothesis

Authors: Nick Whiteley, Annie Gray, Patrick Rubin-Delanchy

Abstract: The Manifold Hypothesis is a widely accepted tenet of Machine Learning which asserts that nominally high-dimensional data are in fact concentrated near a low-dimensional manifold, embedded in high-dimensional space. This phenomenon is observed empirically in many real world situations, has led to development of a wide range of statistical methods in the last few decades, and has been suggested as… ▽ More The Manifold Hypothesis is a widely accepted tenet of Machine Learning which asserts that nominally high-dimensional data are in fact concentrated near a low-dimensional manifold, embedded in high-dimensional space. This phenomenon is observed empirically in many real world situations, has led to development of a wide range of statistical methods in the last few decades, and has been suggested as a key factor in the success of modern AI technologies. We show that rich and sometimes intricate manifold structure in data can emerge from a generic and remarkably simple statistical model -- the Latent Metric Model -- via elementary concepts such as latent variables, correlation and stationarity. This establishes a general statistical explanation for why the Manifold Hypothesis seems to hold in so many situations. Informed by the Latent Metric Model we derive procedures to discover and interpret the geometry of high-dimensional data, and explore hypotheses about the data generating mechanism. These procedures operate under minimal assumptions and make use of well known graph-analytic algorithms. △ Less

Submitted 21 March, 2025; v1 submitted 24 August, 2022; originally announced August 2022.

MSC Class: 62R20; 62R40; 62G05; 62G20; 62R07; 62-08; 62H25; 62H30

Using Elo Rating as a Metric for Comparative Judgement in Educational Assessment

Authors: Andy Gray, Alma Rahat, Tom Crick, Stephen Lindsay, Darren Wallace

Abstract: Marking and feedback are essential features of teaching and learning, across the overwhelming majority of educational settings and contexts. However, it can take a great deal of time and effort for teachers to mark assessments, and to provide useful feedback to the students. Furthermore, it also creates a significant cognitive load on the assessors, especially in ensuring fairness and equity. Ther… ▽ More Marking and feedback are essential features of teaching and learning, across the overwhelming majority of educational settings and contexts. However, it can take a great deal of time and effort for teachers to mark assessments, and to provide useful feedback to the students. Furthermore, it also creates a significant cognitive load on the assessors, especially in ensuring fairness and equity. Therefore, an alternative approach to marking called comparative judgement (CJ) has been proposed in the educational space. Inspired by the law of comparative judgment (LCJ). This pairwise comparison for as many pairs as possible can then be used to rank all submissions. Studies suggest that CJ is highly reliable and accurate while making it quick for the teachers. Alternative studies have questioned this claim suggesting that the process can increase bias in the results as the same submission is shown many times to an assessor for increasing reliability. Additionally, studies have also found that CJ can result in the overall marking process taking longer than a more traditional method of marking as information about many pairs must be collected. In this paper, we investigate Elo, which has been extensively used in rating players in zero-sum games such as chess. We experimented on a large-scale Twitter dataset on the topic of a recent major UK political event ("Brexit", the UK's political exit from the European Union) to ask users which tweet they found funnier between a pair selected from ten tweets. Our analysis of the data reveals that the Elo rating is statistically significantly similar to the CJ ranking with a Kendall's tau score of 0.96 and a p-value of 1.5x10^(-5). We finish with an informed discussion regarding the potential wider application of this approach to a range of educational contexts. △ Less

Submitted 4 April, 2022; originally announced April 2022.

Comments: 12 pages, 4 figures, one table, pre-review version

A Benchmark for Generalizable and Interpretable Temporal Question Answering over Knowledge Bases

Authors: Sumit Neelam, Udit Sharma, Hima Karanam, Shajith Ikbal, Pavan Kapanipathi, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Young-Suk Lee, Santosh Srivastava, Cezar Pendus, Saswati Dana, Dinesh Garg, Achille Fokoue, G P Shrivatsa Bhargav, Dinesh Khandelwal, Srinivas Ravishankar, Sairam Gurajada, Maria Chang, Rosario Uceda-Sosa, Salim Roukos, Alexander Gray, Guilherme Lima, Ryan Riegel, Francois Luus, L Venkata Subramaniam

Abstract: Knowledge Base Question Answering (KBQA) tasks that involve complex reasoning are emerging as an important research direction. However, most existing KBQA datasets focus primarily on generic multi-hop reasoning over explicit facts, largely ignoring other reasoning types such as temporal, spatial, and taxonomic reasoning. In this paper, we present a benchmark dataset for temporal reasoning, TempQA-… ▽ More Knowledge Base Question Answering (KBQA) tasks that involve complex reasoning are emerging as an important research direction. However, most existing KBQA datasets focus primarily on generic multi-hop reasoning over explicit facts, largely ignoring other reasoning types such as temporal, spatial, and taxonomic reasoning. In this paper, we present a benchmark dataset for temporal reasoning, TempQA-WD, to encourage research in extending the present approaches to target a more challenging set of complex reasoning tasks. Specifically, our benchmark is a temporal question answering dataset with the following advantages: (a) it is based on Wikidata, which is the most frequently curated, openly available knowledge base, (b) it includes intermediate sparql queries to facilitate the evaluation of semantic parsing based approaches for KBQA, and (c) it generalizes to multiple knowledge bases: Freebase and Wikidata. The TempQA-WD dataset is available at https://github.com/IBM/tempqa-wd. △ Less

Submitted 15 January, 2022; originally announced January 2022.

Comments: 7 pages, 2 figures, 7 tables. arXiv admin note: substantial text overlap with arXiv:2109.13430

A Simple Standard for Sharing Ontological Mappings (SSSOM)

Authors: Nicolas Matentzoglu, James P. Balhoff, Susan M. Bello, Chris Bizon, Matthew Brush, Tiffany J. Callahan, Christopher G Chute, William D. Duncan, Chris T. Evelo, Davera Gabriel, John Graybeal, Alasdair Gray, Benjamin M. Gyori, Melissa Haendel, Henriette Harmse, Nomi L. Harris, Ian Harrow, Harshad Hegde, Amelia L. Hoyt, Charles T. Hoyt, Dazhi Jiao, Ernesto Jiménez-Ruiz, Simon Jupp, Hyeongsik Kim, Sebastian Koehler , et al. (19 additional authors not shown)

Abstract: Despite progress in the development of standards for describing and exchanging scientific information, the lack of easy-to-use standards for mapping between different representations of the same or similar objects in different databases poses a major impediment to data integration and interoperability. Mappings often lack the metadata needed to be correctly interpreted and applied. For example, ar… ▽ More Despite progress in the development of standards for describing and exchanging scientific information, the lack of easy-to-use standards for mapping between different representations of the same or similar objects in different databases poses a major impediment to data integration and interoperability. Mappings often lack the metadata needed to be correctly interpreted and applied. For example, are two terms equivalent or merely related? Are they narrow or broad matches? Are they associated in some other way? Such relationships between the mapped terms are often not documented, leading to incorrect assumptions and making them hard to use in scenarios that require a high degree of precision (such as diagnostics or risk prediction). Also, the lack of descriptions of how mappings were done makes it hard to combine and reconcile mappings, particularly curated and automated ones. The Simple Standard for Sharing Ontological Mappings (SSSOM) addresses these problems by: 1. Introducing a machine-readable and extensible vocabulary to describe metadata that makes imprecision, inaccuracy and incompleteness in mappings explicit. 2. Defining an easy to use table-based format that can be integrated into existing data science pipelines without the need to parse or query ontologies, and that integrates seamlessly with Linked Data standards. 3. Implementing open and community-driven collaborative workflows designed to evolve the standard continuously to address changing requirements and mapping practices. 4. Providing reference tools and software libraries for working with the standard. In this paper, we present the SSSOM standard, describe several use cases, and survey some existing work on standardizing the exchange of mappings, with the goal of making mappings Findable, Accessible, Interoperable, and Reusable (FAIR). The SSSOM specification is at http://w3id.org/sssom/spec. △ Less

Submitted 13 December, 2021; originally announced December 2021.

Comments: Corresponding author: Christopher J. Mungall <cjmungall@lbl.gov>

Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks

Authors: Prithviraj Sen, Breno W. S. R. de Carvalho, Ryan Riegel, Alexander Gray

Abstract: Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approximate logical operators with differentiable operators from fuzzy or real-valued logic that are parameter-free thus diminishing their capacity to fit the data, other approaches are only loosely based on logic making it dif… ▽ More Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approximate logical operators with differentiable operators from fuzzy or real-valued logic that are parameter-free thus diminishing their capacity to fit the data, other approaches are only loosely based on logic making it difficult to interpret the learned "rules". In this paper, we propose learning rules with the recently proposed logical neural networks (LNN). Compared to others, LNNs offer strong connection to classical Boolean logic thus allowing for precise interpretation of learned rules while harboring parameters that can be trained with gradient-based optimization to effectively fit the data. We extend LNNs to induce rules in first-order logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable and can achieve comparable or higher accuracy due to their flexible parameterization. △ Less

Submitted 6 December, 2021; originally announced December 2021.

LOA: Logical Optimal Actions for Text-based Interaction Games

Authors: Daiki Kimura, Subhajit Chaudhury, Masaki Ono, Michiaki Tatsubori, Don Joven Agravante, Asim Munawar, Akifumi Wachi, Ryosuke Kohita, Alexander Gray

Abstract: We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. The demonstration for LOA experiments consists of a web-based interactive platform for text-based games and visualization for acqu… ▽ More We present Logical Optimal Actions (LOA), an action decision architecture of reinforcement learning applications with a neuro-symbolic framework which is a combination of neural network and symbolic knowledge acquisition approach for natural language interaction games. The demonstration for LOA experiments consists of a web-based interactive platform for text-based games and visualization for acquired knowledge for improving interpretability for trained rules. This demonstration also provides a comparison module with other neuro-symbolic approaches as well as non-symbolic state-of-the-art agent models on the same text-based games. Our LOA also provides open-sourced implementation in Python for the reinforcement learning environment to facilitate an experiment for studying neuro-symbolic agents. Code: https://github.com/ibm/loa △ Less

Submitted 21 October, 2021; originally announced October 2021.

Comments: ACL-IJCNLP 2021 (demo paper)

Neuro-Symbolic Reinforcement Learning with First-Order Logic

Authors: Daiki Kimura, Masaki Ono, Subhajit Chaudhury, Ryosuke Kohita, Akifumi Wachi, Don Joven Agravante, Michiaki Tatsubori, Asim Munawar, Alexander Gray

Abstract: Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules… ▽ More Deep reinforcement learning (RL) methods often require many trials before convergence, and no direct interpretability of trained policies is provided. In order to achieve fast convergence and interpretability for the policy in RL, we propose a novel RL method for text-based games with a recent neuro-symbolic framework called Logical Neural Network, which can learn symbolic and interpretable rules in their differentiable network. The method is first to extract first-order logical facts from text observation and external word meaning network (ConceptNet), then train a policy in the network with directly interpretable logical operators. Our experimental results show RL training with the proposed method converges significantly faster than other state-of-the-art neuro-symbolic methods in a TextWorld benchmark. △ Less

Submitted 21 October, 2021; originally announced October 2021.

Comments: EMNLP 2021 (main conference)

SPaR.txt, a cheap Shallow Parsing approach for Regulatory texts

Authors: Ruben Kruiper, Ioannis Konstas, Alasdair Gray, Farhad Sadeghineko, Richard Watson, Bimal Kumar

Abstract: Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shal… ▽ More Automated Compliance Checking (ACC) systems aim to semantically parse building regulations to a set of rules. However, semantic parsing is known to be hard and requires large amounts of training data. The complexity of creating such training data has led to research that focuses on small sub-tasks, such as shallow parsing or the extraction of a limited subset of rules. This study introduces a shallow parsing task for which training data is relatively cheap to create, with the aim of learning a lexicon for ACC. We annotate a small domain-specific dataset of 200 sentences, SPaR.txt, and train a sequence tagger that achieves 79,93 F1-score on the test set. We then show through manual evaluation that the model identifies most (89,84%) defined terms in a set of building regulation documents, and that both contiguous and discontiguous Multi-Word Expressions (MWE) are discovered with reasonable accuracy (70,3%). △ Less

Submitted 4 October, 2021; originally announced October 2021.

Comments: To be published in the NLLP workshop at EMNLP 2021, 9 pages (15 including reference and appendices). For the ScotReg corpus, SPaR.txt dataset and code see: http://github.com/rubenkruiper/SPaR.txt

SYGMA: System for Generalizable Modular Question Answering OverKnowledge Bases

Authors: Sumit Neelam, Udit Sharma, Hima Karanam, Shajith Ikbal, Pavan Kapanipathi, Ibrahim Abdelaziz, Nandana Mihindukulasooriya, Young-Suk Lee, Santosh Srivastava, Cezar Pendus, Saswati Dana, Dinesh Garg, Achille Fokoue, G P Shrivatsa Bhargav, Dinesh Khandelwal, Srinivas Ravishankar, Sairam Gurajada, Maria Chang, Rosario Uceda-Sosa, Salim Roukos, Alexander Gray, Guilherme LimaRyan Riegel, Francois Luus, L Venkata Subramaniam

Abstract: Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are emerging as an important re-search direction. However, most KBQA systems struggle withgeneralizability, particularly on two dimensions: (a) acrossmultiple reasoning types where both datasets and systems haveprimarily focused on multi-hop reasoning, and (b) across mul-tiple knowledge bases, where KBQA approaches are… ▽ More Knowledge Base Question Answering (KBQA) tasks that in-volve complex reasoning are emerging as an important re-search direction. However, most KBQA systems struggle withgeneralizability, particularly on two dimensions: (a) acrossmultiple reasoning types where both datasets and systems haveprimarily focused on multi-hop reasoning, and (b) across mul-tiple knowledge bases, where KBQA approaches are specif-ically tuned to a single knowledge base. In this paper, wepresent SYGMA, a modular approach facilitating general-izability across multiple knowledge bases and multiple rea-soning types. Specifically, SYGMA contains three high levelmodules: 1) KB-agnostic question understanding module thatis common across KBs 2) Rules to support additional reason-ing types and 3) KB-specific question mapping and answeringmodule to address the KB-specific aspects of the answer ex-traction. We demonstrate effectiveness of our system by evalu-ating on datasets belonging to two distinct knowledge bases,DBpedia and Wikidata. In addition, to demonstrate extensi-bility to additional reasoning types we evaluate on multi-hopreasoning datasets and a new Temporal KBQA benchmarkdataset on Wikidata, namedTempQA-WD1, introduced in thispaper. We show that our generalizable approach has bettercompetetive performance on multiple datasets on DBpediaand Wikidata that requires both multi-hop and temporal rea-soning △ Less

Submitted 27 September, 2021; originally announced September 2021.

Logical Credal Networks

Authors: Haifeng Qian, Radu Marinescu, Alexander Gray, Debarun Bhattacharjya, Francisco Barahona, Tian Gao, Ryan Riegel, Pravinda Sahu

Abstract: This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability. Given imprecise information represented by probability bounds and conditional probability bounds of logic formulas, this logic specifies a set of probability distributions over all interpretations. On the one hand, our approach allows propositional… ▽ More This paper introduces Logical Credal Networks, an expressive probabilistic logic that generalizes many prior models that combine logic and probability. Given imprecise information represented by probability bounds and conditional probability bounds of logic formulas, this logic specifies a set of probability distributions over all interpretations. On the one hand, our approach allows propositional and first-order logic formulas with few restrictions, e.g., without requiring acyclicity. On the other hand, it has a Markov condition similar to Bayesian networks and Markov random fields that is critical in real-world applications. Having both these properties makes this logic unique, and we investigate its performance on maximum a posteriori inference tasks, including solving Mastermind games with uncertainty and detecting credit card fraud. The results show that the proposed method outperforms existing approaches, and its advantage lies in aggregating multiple sources of imprecise information. △ Less

Submitted 24 September, 2021; originally announced September 2021.