Showing 1–50 of 70 results for author: Leung, K K

BALANCE: Hybrid Autoregressive-Speculative LLM Inference in Wireless Edge Networks

Authors: Guanqiao Qu, Shuo Chen, Qian Chen, Kin K. Leung, Xianhao Chen

Abstract: Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference mainly relies on two approaches: Autoregressive decoding (AD) generates output tokens sequentially, resulting in long latency; Speculative decoding (SD) accelerates inference by using a small language model (SLM) to generate multiple draft tokens for LLM… ▽ More Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference mainly relies on two approaches: Autoregressive decoding (AD) generates output tokens sequentially, resulting in long latency; Speculative decoding (SD) accelerates inference by using a small language model (SLM) to generate multiple draft tokens for LLM verification, but incurs extra memory costs. Due to this latency-memory tradeoff, neither approach alone can efficiently serve users with heterogeneous demands under limited edge computing resources. To address this challenge, we propose a hybrid autoregressive-speculative inference (BALANCE) framework for edge LLM inference. In BALANCE, an edge server hosts both an SLM and an LLM, assigns each user to AD or SD, and performs the two modes simultaneously. To maximize the number of served users, we formulate a task throughput maximization problem to jointly determine user scheduling and computing resource allocation between AD and SD under user latency requirements and server memory constraints. Since the problem is NP-hard, we develop a polynomial-time algorithm that transforms the original problem into two sub-problems and obtains a sub-optimal solution with a constant approximation guarantee. Experiments demonstrate that BALANCE consistently outperforms conventional AD and SD and significantly improves task throughput. △ Less

Submitted 6 August, 2026; originally announced August 2026.

Comments: 10 pages, 7 figures

RL-based Joint Coverage and Beam Optimization of High Altitude Platform Systems

Authors: Guilhem Loussouarn, Nancy Nayak, Kin K. Leung, Patrick J. Baker

Abstract: High Altitude Platform Systems (HAPS) are a promising component of 6G network architectures, offering a unique "freedom of movement" that distinguishes them from static terrestrial networks (TN) and orbit-constrained satellite communications. This inherent mobility for HAPS provides a powerful mechanism to address non-stationarity, spatio-temporal user distributions, and traffic dynamics, such as… ▽ More High Altitude Platform Systems (HAPS) are a promising component of 6G network architectures, offering a unique "freedom of movement" that distinguishes them from static terrestrial networks (TN) and orbit-constrained satellite communications. This inherent mobility for HAPS provides a powerful mechanism to address non-stationarity, spatio-temporal user distributions, and traffic dynamics, such as periodic population migrations. This work addresses three key optimization problems in HAPS networks: (a) HAPS positioning for optimal coverage, (b) beam allocation, and (c) joint optimization of coverage and beam allocation. To tackle these complex challenges, a Reinforcement Learning (RL) framework is proposed, capable of operating in scenarios with multiple HAPS. The results demonstrate that the RL-based approach effectively learns to control HAPS positioning and resource allocation, dynamically adapting to variations in user distributions and traffic patterns. In particular, by employing a multi-policy Proximal Policy Optimization (PPO) approach, the proposed framework jointly learns HAPS positioning and allocating beams under spatio-temporal traffic demand variations and outperforms heuristic baselines. Simulation results demonstrate that our joint optimization approach significantly improves sum-rate and user satisfaction, showing that the dynamic mobility of HAPS can be successfully exploited to create highly responsive and efficient next-generation networks. △ Less

Submitted 5 May, 2026; originally announced June 2026.

Conf-Gen: Conformal Uncertainty Quantification for Generative Models

Authors: Gabriel Loaiza-Ganem, Kevin Zhang, Wei Cui, Marc T. Law, Kin Kwan Leung

Abstract: Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machine learning through formal guarantees. However, recent breakthroughs in artificial intelligence (AI) have been driven by unsupervised generative models, such as large language models (LLMs) and image generators, which are not directly compatible with… ▽ More Conformal prediction (CP) and its extension, conformal risk control (CRC), are established frameworks for quantifying uncertainty in supervised machine learning through formal guarantees. However, recent breakthroughs in artificial intelligence (AI) have been driven by unsupervised generative models, such as large language models (LLMs) and image generators, which are not directly compatible with CP or CRC. In this work we introduce conformal generation (Conf-Gen), a general framework adapting CRC to generative tasks while relaxing its theoretical assumptions. Conf-Gen unifies and generalizes previous attempts to apply CP to LLMs, and extends conformal methodology to entirely new domains. We demonstrate the flexibility of Conf-Gen through some novel applications, including obtaining conformal guarantees on: image generators producing non-memorized images, conversational AI systems having asked enough clarifying questions, and the output of AI agents being correct. △ Less

Submitted 27 May, 2026; originally announced May 2026.

Comments: ICML 2026

Quantum Networking Fundamentals: From Physical Protocols to Network Engineering

Authors: Athanasios Gkelias, Felix T. A. Burt, Kin K. Leung

Abstract: The realization of the Quantum Internet promises transformative capabilities in secure communication, distributed quantum computing, and high-precision metrology. However, transitioning from laboratory experiments to a scalable, multi-tenant network utility introduces deep orchestration challenges. Current development is often siloed within physics communities, prioritizing hardware, while the cla… ▽ More The realization of the Quantum Internet promises transformative capabilities in secure communication, distributed quantum computing, and high-precision metrology. However, transitioning from laboratory experiments to a scalable, multi-tenant network utility introduces deep orchestration challenges. Current development is often siloed within physics communities, prioritizing hardware, while the classical networking community lacks architectural models to manage fragile quantum resources. This tutorial bridges this divide by providing a network-centric view of quantum networking. We dismantle idealized assumptions in current simulators to address the "simulation-reality gap," recasting them as explicit control-plane constraints. To bridge this gap, we establish Software-Defined Quantum Networking (SDQN) as a prerequisite for scale, prioritizing a symbiotic, dual-plane architecture where classical control dictates quantum data flow. Specifically, we synthesize reference models for SDQN and the Quantum Network Operating System (QNOS) for hardware abstraction, and adapt a Quantum Network Utility Maximization (Q-NUM) framework as a unifying mathematical lens for engineers to reason about trade-offs between entanglement routing, scheduling, and fidelity. Furthermore, we analyze Distributed Quantum AI (DQAI) over imperfect networks as a case study, illustrating how physical constraints such as probabilistic stragglers and decoherence dictate application-layer viability. Ultimately, this tutorial equips network engineers with the tools required to transition quantum networking from a bespoke physics experiment into a programmable, multi-tenant global infrastructure. △ Less

Submitted 2 April, 2026; originally announced April 2026.

Comments: Submitted to IEEE Communications Surveys and Tutorials

Photonic Quantum-Enhanced Knowledge Distillation

Authors: Kuan-Cheng Chen, Shang Yu, Chen-Yu Liu, Samuel Yen-Chi Chen, Huan-Hsin Tseng, Yen Jui Chang, Wei-Hao Huang, Felix Burt, Esperanza Cuenca Gomez, Zohim Chandani, William Clements, Ian Walmsley, Kin K. Leung

Abstract: Photonic quantum processors naturally produce intrinsically stochastic measurement outcomes, offering a hardware-native source of structured randomness that can be exploited during machine-learning training. Here we introduce Photonic Quantum-Enhanced Knowledge Distillation (PQKD), a hybrid quantum photonic--classical framework in which a programmable photonic circuit generates a compact condition… ▽ More Photonic quantum processors naturally produce intrinsically stochastic measurement outcomes, offering a hardware-native source of structured randomness that can be exploited during machine-learning training. Here we introduce Photonic Quantum-Enhanced Knowledge Distillation (PQKD), a hybrid quantum photonic--classical framework in which a programmable photonic circuit generates a compact conditioning signal that constrains and guides a parameter-efficient student network during distillation from a high-capacity teacher. PQKD replaces fully trainable convolutional kernels with dictionary convolutions: each layer learns only a small set of shared spatial basis filters, while sample-dependent channel-mixing weights are derived from shot-limited photonic features and mapped through a fixed linear transform. Training alternates between standard gradient-based optimisation of the student and sampling-robust, gradient-free updates of photonic parameters, avoiding differentiation through photonic hardware. Across MNIST, Fashion-MNIST and CIFAR-10, PQKD traces a controllable compression--accuracy frontier, remaining close to teacher performance on simpler benchmarks under aggressive convolutional compression. Performance degrades predictably with finite sampling, consistent with shot-noise scaling, and exponential moving-average feature smoothing suppresses high-frequency shot-noise fluctuations, extending the practical operating regime at moderate shot budgets. △ Less

Submitted 16 March, 2026; originally announced March 2026.

Consensus Protocols for Entanglement-Aware Scheduling in Distributed Quantum Neural Networks

Authors: Kuan-Cheng Chen, Samuel Yen-Chi Chen, Mahdi Chehimi, Felix Burt, Kin K. Leung

Abstract: The realization of distributed quantum neural networks (DQNNs) over quantum internet infrastructures faces fundamental challenges arising from the fragile nature of entanglement and the demanding synchronization requirements of distributed learning. We introduce a Consensus-Entanglement-Aware Scheduling (CEAS) framework that co-designs quantum consensus protocols with adaptive entanglement managem… ▽ More The realization of distributed quantum neural networks (DQNNs) over quantum internet infrastructures faces fundamental challenges arising from the fragile nature of entanglement and the demanding synchronization requirements of distributed learning. We introduce a Consensus-Entanglement-Aware Scheduling (CEAS) framework that co-designs quantum consensus protocols with adaptive entanglement management to enable robust synchronous training across distributed quantum processors. CEAS integrates fidelity-weighted aggregation, in which parameter updates are weighted by quantum Fisher information to suppress noisy contributions, with decoherence-aware entanglement scheduling that treats Bell pairs as perishable resources subject to exponential decay. The framework incorporates quantum-authenticated Byzantine fault tolerance, ensuring security against malicious nodes while maintaining compatibility with noisy intermediate-scale quantum (NISQ) constraints. Our theoretical analysis establishes convergence guarantees under heterogeneous noise conditions, while numerical simulations demonstrate that CEAS maintains 10-15 percentage points higher accuracy compared to entanglement-oblivious baselines under coordinated Byzantine attacks, achieving 90 percent Bell-pair utilization despite coherence time limitations. This work provides a foundational architecture for scalable distributed quantum machine learning, bridging quantum networking, distributed optimization, and early fault-tolerant quantum computation. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Adaptive Resource Orchestration for Distributed Quantum Computing Systems

Authors: Kuan-Cheng Chen, Felix Burt, Nitish K. Panigrahy, Kin K. Leung

Abstract: Scaling quantum computing beyond a single device requires networking many quantum processing units (QPUs) into a coherent quantum-HPC system. We propose the Modular Entanglement Hub (ModEn-Hub) architecture: a hub-and-spoke photonic interconnect paired with a real-time quantum network orchestrator. ModEn-Hub centralizes entanglement sources and shared quantum memory to deliver on-demand, high-fide… ▽ More Scaling quantum computing beyond a single device requires networking many quantum processing units (QPUs) into a coherent quantum-HPC system. We propose the Modular Entanglement Hub (ModEn-Hub) architecture: a hub-and-spoke photonic interconnect paired with a real-time quantum network orchestrator. ModEn-Hub centralizes entanglement sources and shared quantum memory to deliver on-demand, high-fidelity Bell pairs across heterogeneous QPUs, while the control plane schedules teleportation-based non-local gates, launches parallel entanglement attempts, and maintains a small ebit cache. To quantify benefits, we implement a lightweight, reproducible Monte Carlo study under realistic loss and tight round budgets, comparing a naive sequential baseline to an orchestrated policy with logarithmically scaled parallelism and opportunistic caching. Across 1-128 QPUs and 2,500 trials per point, ModEn-Hub-style orchestration sustains about 90% teleportation success while the baseline degrades toward about 30%, at the cost of higher average entanglement attempts (about 10-12 versus about 3). These results provide clear, high-level evidence that adaptive resource orchestration in the ModEn-Hub enables scalable and efficient quantum-HPC operation on near-term hardware. △ Less

Submitted 31 December, 2025; originally announced December 2025.

Federated Quantum Kernel Learning for Anomaly Detection in Multivariate IoT Time-Series

Authors: Kuan-Cheng Chen, Samuel Yen-Chi Chen, Chen-Yu Liu, Kin K. Leung

Abstract: The rapid growth of industrial Internet of Things (IIoT) systems has created new challenges for anomaly detection in high-dimensional, multivariate time-series, where privacy, scalability, and communication efficiency are critical. Classical federated learning approaches mitigate privacy concerns by enabling decentralized training, but they often struggle with highly non-linear decision boundaries… ▽ More The rapid growth of industrial Internet of Things (IIoT) systems has created new challenges for anomaly detection in high-dimensional, multivariate time-series, where privacy, scalability, and communication efficiency are critical. Classical federated learning approaches mitigate privacy concerns by enabling decentralized training, but they often struggle with highly non-linear decision boundaries and imbalanced anomaly distributions. To address this gap, we propose a Federated Quantum Kernel Learning (FQKL) framework that integrates quantum feature maps with federated aggregation to enable distributed, privacy-preserving anomaly detection across heterogeneous IoT networks. In our design, quantum edge nodes locally compute compressed kernel statistics using parameterized quantum circuits and share only these summaries with a central server, which constructs a global Gram matrix and trains a decision function (e.g., Fed-QSVM). Experimental results on synthetic IIoT benchmarks demonstrate that FQKL achieves superior generalization in capturing complex temporal correlations compared to classical federated baselines, while significantly reducing communication overhead. This work highlights the promise of quantum kernels in federated settings, advancing the path toward scalable, robust, and quantum-enhanced intelligence for next-generation IoT infrastructures. △ Less

Submitted 4 November, 2025; originally announced November 2025.

Classifying and Addressing the Diversity of Errors in Retrieval-Augmented Generation Systems

Authors: Kin Kwan Leung, Mouloud Belbahri, Yi Sui, Alex Labach, Xueying Zhang, Stephen Anthony Rose, Jesse C. Cresswell

Abstract: Retrieval-augmented generation (RAG) is a prevalent approach for building LLM-based question-answering systems that can take advantage of external knowledge databases. Due to the complexity of real-world RAG systems, there are many potential causes for erroneous outputs. Understanding the range of errors that can occur in practice is crucial for robust deployment. We present a new taxonomy of the… ▽ More Retrieval-augmented generation (RAG) is a prevalent approach for building LLM-based question-answering systems that can take advantage of external knowledge databases. Due to the complexity of real-world RAG systems, there are many potential causes for erroneous outputs. Understanding the range of errors that can occur in practice is crucial for robust deployment. We present a new taxonomy of the error types that can occur in realistic RAG systems, examples of each, and practical advice for addressing them. Additionally, we curate a dataset of erroneous RAG responses annotated by error types. We then propose an auto-evaluation method aligned with our taxonomy that can be used in practice to track and address errors during development. Code and data are available at https://github.com/layer6ai-labs/rag-error-classification. △ Less

Submitted 14 January, 2026; v1 submitted 15 October, 2025; originally announced October 2025.

Comments: EACL 2026

Document Summarization with Conformal Importance Guarantees

Authors: Bruce Kuwahara, Chen-Yuan Lin, Xiao Shi Huang, Kin Kwan Leung, Jullian Arta Yapeter, Ilya Stanevich, Felipe Perez, Jesse C. Cresswell

Abstract: Automatic summarization systems have advanced rapidly with large language models (LLMs), yet they still lack reliable guarantees on inclusion of critical content in high-stakes domains like healthcare, law, and finance. In this work, we introduce Conformal Importance Summarization, the first framework for importance-preserving summary generation which uses conformal prediction to provide rigorous,… ▽ More Automatic summarization systems have advanced rapidly with large language models (LLMs), yet they still lack reliable guarantees on inclusion of critical content in high-stakes domains like healthcare, law, and finance. In this work, we introduce Conformal Importance Summarization, the first framework for importance-preserving summary generation which uses conformal prediction to provide rigorous, distribution-free coverage guarantees. By calibrating thresholds on sentence-level importance scores, we enable extractive document summarization with user-specified coverage and recall rates over critical content. Our method is model-agnostic, requires only a small calibration set, and seamlessly integrates with existing black-box LLMs. Experiments on established summarization benchmarks demonstrate that Conformal Importance Summarization achieves the theoretically assured information coverage rate. Our work suggests that Conformal Importance Summarization can be combined with existing techniques to achieve reliable, controllable automatic summarization, paving the way for safer deployment of AI summarization tools in critical applications. Code is available at https://github.com/layer6ai-labs/conformal-importance-summarization. △ Less

Submitted 24 September, 2025; originally announced September 2025.

Comments: NeurIPS 2025. Code is available at https://github.com/layer6ai-labs/conformal-importance-summarization

Quantum Machine Learning for UAV Swarm Intrusion Detection

Authors: Kuan-Cheng Chen, Samuel Yen-Chi Chen, Tai-Yue Li, Chen-Yu Liu, Kin K. Leung

Abstract: Intrusion detection in unmanned-aerial-vehicle (UAV) swarms is complicated by high mobility, non-stationary traffic, and severe class imbalance. Leveraging a 120 k-flow simulation corpus that covers five attack types, we benchmark three quantum-machine-learning (QML) approaches - quantum kernels, variational quantum neural networks (QNNs), and hybrid quantum-trained neural networks (QT-NNs) - agai… ▽ More Intrusion detection in unmanned-aerial-vehicle (UAV) swarms is complicated by high mobility, non-stationary traffic, and severe class imbalance. Leveraging a 120 k-flow simulation corpus that covers five attack types, we benchmark three quantum-machine-learning (QML) approaches - quantum kernels, variational quantum neural networks (QNNs), and hybrid quantum-trained neural networks (QT-NNs) - against strong classical baselines. All models consume an 8-feature flow representation and are evaluated under identical preprocessing, balancing, and noise-model assumptions. We analyse the influence of encoding strategy, circuit depth, qubit count, and shot noise, reporting accuracy, macro-F1, ROC-AUC, Matthews correlation, and quantum-resource footprints. Results reveal clear trade-offs: quantum kernels and QT-NNs excel in low-data, nonlinear regimes, while deeper QNNs suffer from trainability issues, and CNNs dominate when abundant data offset their larger parameter count. The complete codebase and dataset partitions are publicly released to enable reproducible QML research in network security. △ Less

Submitted 1 September, 2025; originally announced September 2025.

Spatial-Temporal Reinforcement Learning for Network Routing with Non-Markovian Traffic

Authors: Molly Wang, Kin. K Leung

Abstract: Reinforcement Learning (RL) has been widely used for packet routing in communication networks, but traditional RL methods rely on the Markov assumption that the current state contains all necessary information for decision-making. In reality, internet traffic is non-Markovian, and past states do influence routing performance. Moreover, common deep RL approaches use function approximators, such as… ▽ More Reinforcement Learning (RL) has been widely used for packet routing in communication networks, but traditional RL methods rely on the Markov assumption that the current state contains all necessary information for decision-making. In reality, internet traffic is non-Markovian, and past states do influence routing performance. Moreover, common deep RL approaches use function approximators, such as neural networks, that do not model the spatial structure in network topologies. To address these shortcomings, we design a network environment with non-Markovian traffic and introduce a spatial-temporal RL (STRL) framework for packet routing. Our approach outperforms traditional baselines by more than 19% during training and 7% for inference despite a change in network topology. △ Less

Submitted 31 July, 2025; v1 submitted 27 July, 2025; originally announced July 2025.

Entanglement-Efficient Distribution of Quantum Circuits over Large-Scale Quantum Networks

Authors: Felix Burt, Kuan-Cheng Chen, Kin K. Leung

Abstract: Quantum computers face inherent scaling challenges, a fact that necessitates investigation of distributed quantum computing systems, whereby scaling is achieved through interconnection of smaller quantum processing units. However, connecting large numbers of QPUs will eventually result in connectivity constraints at the network level, where the difficulty of entanglement sharing increases with net… ▽ More Quantum computers face inherent scaling challenges, a fact that necessitates investigation of distributed quantum computing systems, whereby scaling is achieved through interconnection of smaller quantum processing units. However, connecting large numbers of QPUs will eventually result in connectivity constraints at the network level, where the difficulty of entanglement sharing increases with network path lengths. This increases the complexity of the quantum circuit partitioning problem, since the cost of generating entanglement between end nodes varies with network topologies and existing links. We address this challenge using a simple modification to existing partitioning schemes designed for all-to-all connected networks, that efficiently accounts for both of these factors. We investigate the performance in terms of entanglement requirements and optimisation time of various quantum circuits over different network topologies, achieving lower entanglement costs in the majority of cases than state-of-the-art methods. We provide techniques for scaling to large-scale quantum networks employing both network and problem coarsening. We show that coarsened methods can achieve improved solution quality in most cases with significantly lower run-times than direct partitioning methods. △ Less

Submitted 23 July, 2025; v1 submitted 21 July, 2025; originally announced July 2025.

Comments: 12 pages, 10 figures, to be published in proceedings of IEEE QCE2025

Journal ref: 2025 IEEE International Conference on Quantum Computing and Engineering (QCE)

Special-Unitary Parameterization for Trainable Variational Quantum Circuits

Authors: Kuan-Cheng Chen, Huan-Hsin Tseng, Samuel Yen-Chi Chen, Chen-Yu Liu, Kin K. Leung

Abstract: We propose SUN-VQC, a variational-circuit architecture whose elementary layers are single exponentials of a symmetry-restricted Lie subgroup, $\mathrm{SU}(2^{k}) \subset \mathrm{SU}(2^{n})$ with $k \ll n$. Confining the evolution to this compact subspace reduces the dynamical Lie-algebra dimension from $\mathcal{O}(4^{n})$ to $\mathcal{O}(4^{k})$, ensuring only polynomial suppression of gradient v… ▽ More We propose SUN-VQC, a variational-circuit architecture whose elementary layers are single exponentials of a symmetry-restricted Lie subgroup, $\mathrm{SU}(2^{k}) \subset \mathrm{SU}(2^{n})$ with $k \ll n$. Confining the evolution to this compact subspace reduces the dynamical Lie-algebra dimension from $\mathcal{O}(4^{n})$ to $\mathcal{O}(4^{k})$, ensuring only polynomial suppression of gradient variance and circumventing barren plateaus that plague hardware-efficient ansätze. Exact, hardware-compatible gradients are obtained using a generalized parameter-shift rule, avoiding ancillary qubits and finite-difference bias. Numerical experiments on quantum auto-encoding and classification show that SUN-VQCs sustain order-of-magnitude larger gradient signals, converge 2--3$\times$ faster, and reach higher final fidelities than depth-matched Pauli-rotation or hardware-efficient circuits. These results demonstrate that Lie-subalgebra engineering provides a principled, scalable route to barren-plateau-resilient VQAs compatible with near-term quantum processors. △ Less

Submitted 7 July, 2025; originally announced July 2025.

On Convolutions, Intrinsic Dimension, and Diffusion Models

Authors: Kin Kwan Leung, Rasa Hosseinzadeh, Gabriel Loaiza-Ganem

Abstract: The manifold hypothesis asserts that data of interest in high-dimensional ambient spaces, such as image data, lies on unknown low-dimensional submanifolds. Diffusion models (DMs) -- which operate by convolving data with progressively larger amounts of Gaussian noise and then learning to revert this process -- have risen to prominence as the most performant generative models, and are known to be ab… ▽ More The manifold hypothesis asserts that data of interest in high-dimensional ambient spaces, such as image data, lies on unknown low-dimensional submanifolds. Diffusion models (DMs) -- which operate by convolving data with progressively larger amounts of Gaussian noise and then learning to revert this process -- have risen to prominence as the most performant generative models, and are known to be able to learn distributions with low-dimensional support. For a given datum in one of these submanifolds, we should thus intuitively expect DMs to have implicitly learned its corresponding local intrinsic dimension (LID), i.e. the dimension of the submanifold it belongs to. Kamkari et al. (2024b) recently showed that this is indeed the case by linking this LID to the rate of change of the log marginal densities of the DM with respect to the amount of added noise, resulting in an LID estimator known as FLIPD. LID estimators such as FLIPD have a plethora of uses, among others they quantify the complexity of a given datum, and can be used to detect outliers, adversarial examples and AI-generated text. FLIPD achieves state-of-the-art performance at LID estimation, yet its theoretical underpinnings are incomplete since Kamkari et al. (2024b) only proved its correctness under the highly unrealistic assumption of affine submanifolds. In this work we bridge this gap by formally proving the correctness of FLIPD under realistic assumptions. Additionally, we show that an analogous result holds when Gaussian convolutions are replaced with uniform ones, and discuss the relevance of this result. △ Less

Submitted 13 October, 2025; v1 submitted 25 June, 2025; originally announced June 2025.

Comments: TMLR 2025 (expert certification)

Textual Bayes: Quantifying Prompt Uncertainty in LLM-Based Systems

Authors: Brendan Leigh Ross, Noël Vouitsis, Atiyeh Ashari Ghomi, Rasa Hosseinzadeh, Ji Xin, Zhaoyan Liu, Yi Sui, Shiyi Hou, Kin Kwan Leung, Gabriel Loaiza-Ganem, Jesse C. Cresswell

Abstract: Although large language models (LLMs) are becoming increasingly capable of solving challenging real-world tasks, accurately quantifying their uncertainty remains a critical open problem--one that limits their applicability in high-stakes domains. This challenge is further compounded by the closed-source, black-box nature of many state-of-the-art LLMs. Moreover, LLM-based systems can be highly sens… ▽ More Although large language models (LLMs) are becoming increasingly capable of solving challenging real-world tasks, accurately quantifying their uncertainty remains a critical open problem--one that limits their applicability in high-stakes domains. This challenge is further compounded by the closed-source, black-box nature of many state-of-the-art LLMs. Moreover, LLM-based systems can be highly sensitive to the prompts that bind them together, which often require significant manual tuning (i.e., prompt engineering). In this work, we address these challenges by viewing LLM-based systems through a Bayesian lens. We interpret prompts as textual parameters in a statistical model, allowing us to use a small training dataset to perform Bayesian inference over these prompts. This novel perspective enables principled uncertainty quantification over both the model's textual parameters and its downstream predictions, while also incorporating prior beliefs about these parameters expressed in free-form text. To perform Bayesian inference--a difficult problem even for well-studied data modalities--we introduce Metropolis-Hastings through LLM Proposals (MHLP), a novel Markov chain Monte Carlo (MCMC) algorithm that combines prompt optimization techniques with standard MCMC methods. MHLP is a turnkey modification to existing LLM pipelines, including those that rely exclusively on closed-source models. Empirically, we demonstrate that our method yields improvements in both predictive accuracy and uncertainty quantification (UQ) on a range of LLM benchmarks and UQ tasks. More broadly, our work demonstrates a viable path for incorporating methods from the rich Bayesian literature into the era of LLMs, paving the way for more reliable and calibrated LLM-based systems. △ Less

Submitted 17 April, 2026; v1 submitted 11 June, 2025; originally announced June 2025.

Comments: ICLR 2026

Distributed Quantum Neural Networks on Distributed Photonic Quantum Computing

Authors: Kuan-Cheng Chen, Chen-Yu Liu, Yu Shang, Felix Burt, Kin K. Leung

Abstract: We introduce a distributed quantum-classical framework that synergizes photonic quantum neural networks (QNNs) with matrix-product-state (MPS) mapping to achieve parameter-efficient training of classical neural networks. By leveraging universal linear-optical decompositions of $M$-mode interferometers and photon-counting measurement statistics, our architecture generates neural parameters through… ▽ More We introduce a distributed quantum-classical framework that synergizes photonic quantum neural networks (QNNs) with matrix-product-state (MPS) mapping to achieve parameter-efficient training of classical neural networks. By leveraging universal linear-optical decompositions of $M$-mode interferometers and photon-counting measurement statistics, our architecture generates neural parameters through a hybrid quantum-classical workflow: photonic QNNs with $M(M+1)/2$ trainable parameters produce high-dimensional probability distributions that are mapped to classical network weights via an MPS model with bond dimension $χ$. Empirical validation on MNIST classification demonstrates that photonic QT achieves an accuracy of $95.50\% \pm 0.84\%$ using 3,292 parameters ($χ= 10$), compared to $96.89\% \pm 0.31\%$ for classical baselines with 6,690 parameters. Moreover, a ten-fold compression ratio is achieved at $χ= 4$, with a relative accuracy loss of less than $3\%$. The framework outperforms classical compression techniques (weight sharing/pruning) by 6--12\% absolute accuracy while eliminating quantum hardware requirements during inference through classical deployment of compressed parameters. Simulations incorporating realistic photonic noise demonstrate the framework's robustness to near-term hardware imperfections. Ablation studies confirm quantum necessity: replacing photonic QNNs with random inputs collapses accuracy to chance level ($10.0\% \pm 0.5\%$). Photonic quantum computing's room-temperature operation, inherent scalability through spatial-mode multiplexing, and HPC-integrated architecture establish a practical pathway for distributed quantum machine learning, combining the expressivity of photonic Hilbert spaces with the deployability of classical neural networks. △ Less

Submitted 13 May, 2025; originally announced May 2025.

Belief States for Cooperative Multi-Agent Reinforcement Learning under Partial Observability

Authors: Paul J. Pritz, Kin K. Leung

Abstract: Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn simultaneously and influence the underlying state as well as each others' observations. We propose the use of learned beliefs on the underlying state of the syste… ▽ More Reinforcement learning in partially observable environments is typically challenging, as it requires agents to learn an estimate of the underlying system state. These challenges are exacerbated in multi-agent settings, where agents learn simultaneously and influence the underlying state as well as each others' observations. We propose the use of learned beliefs on the underlying state of the system to overcome these challenges and enable reinforcement learning with fully decentralized training and execution. Our approach leverages state information to pre-train a probabilistic belief model in a self-supervised fashion. The resulting belief states, which capture both inferred state information as well as uncertainty over this information, are then used in a state-based reinforcement learning algorithm to create an end-to-end model for cooperative multi-agent reinforcement learning under partial observability. By separating the belief and reinforcement learning tasks, we are able to significantly simplify the policy and value function learning tasks and improve both the convergence speed and the final performance. We evaluate our proposed method on diverse partially observable multi-agent tasks designed to exhibit different variants of partial observability. △ Less

Submitted 11 April, 2025; originally announced April 2025.

Digital Twins for Internet of Battlespace Things (IoBT) Coalitions

Authors: Athanasios Gkelias, Patrick J. Baker, Kin K. Leung, Olwen Worthington, Christopher R. Melville

Abstract: This paper presents a new framework for integrating Digital Twins (DTs) within Internet of battlespace Things (IoBT) coalitions. We introduce a novel three-tier architecture that enables efficient coordination and management of DT models across coalition partners while addressing key challenges in interoperability, security, and resource allocation. The architecture comprises specialized controlle… ▽ More This paper presents a new framework for integrating Digital Twins (DTs) within Internet of battlespace Things (IoBT) coalitions. We introduce a novel three-tier architecture that enables efficient coordination and management of DT models across coalition partners while addressing key challenges in interoperability, security, and resource allocation. The architecture comprises specialized controllers at each tier: Digital Twin Coalition Partner (DTCP) controllers managing individual coalition partners' DT resources, a central Digital Twin Coalition(DTC) controller orchestrating cross-partner coordination, and Digital Twin Coalition Mission (DTCP) controllers handling mission-specific DT interactions. We propose a hybrid approach for DT model placement across edge devices, tactical nodes, and cloud infrastructure, optimizing performance while maintaining security and accessibility. The architecture leverages software-defined networking principles for dynamic resource allocation and slice management, enabling efficient sharing of computational and network resources between DT operations and primary IoBT functions. Our proposed framework aims to provide a robust foundation for deploying and managing Digital Twins in coalition warfare, enhancing situational awareness, decision-making capabilities, and operational effectiveness while ensuring secure and interoperable operations across diverse coalition partners. △ Less

Submitted 3 April, 2025; originally announced April 2025.

Journal ref: STO-MP-IST-209, 2025

Toward Large-Scale Distributed Quantum Long Short-Term Memory with Modular Quantum Computers

Authors: Kuan-Cheng Chen, Samuel Yen-Chi Chen, Chen-Yu Liu, Kin K. Leung

Abstract: In this work, we introduce a Distributed Quantum Long Short-Term Memory (QLSTM) framework that leverages modular quantum computing to address scalability challenges on Noisy Intermediate-Scale Quantum (NISQ) devices. By embedding variational quantum circuits into LSTM cells, the QLSTM captures long-range temporal dependencies, while a distributed architecture partitions the underlying Variational… ▽ More In this work, we introduce a Distributed Quantum Long Short-Term Memory (QLSTM) framework that leverages modular quantum computing to address scalability challenges on Noisy Intermediate-Scale Quantum (NISQ) devices. By embedding variational quantum circuits into LSTM cells, the QLSTM captures long-range temporal dependencies, while a distributed architecture partitions the underlying Variational Quantum Circuits (VQCs) into smaller, manageable subcircuits that can be executed on a network of quantum processing units. We assess the proposed framework using nontrivial benchmark problems such as damped harmonic oscillators and Nonlinear Autoregressive Moving Average sequences. Our results demonstrate that the distributed QLSTM achieves stable convergence and improved training dynamics compared to classical approaches. This work underscores the potential of modular, distributed quantum computing architectures for large-scale sequence modelling, providing a foundation for the future integration of hybrid quantum-classical solutions into advanced Quantum High-performance computing (HPC) ecosystems. △ Less

Submitted 18 March, 2025; originally announced March 2025.

Ultra-Low-Latency Edge Intelligent Sensing: A Source-Channel Tradeoff and Its Application to Coding Rate Adaptation

Authors: Qunsong Zeng, Jianhao Huang, Zhanwei Wang, Kaibin Huang, Kin K. Leung

Abstract: The forthcoming sixth-generation (6G) mobile network is set to merge edge artificial intelligence (AI) and integrated sensing and communication (ISAC) extensively, giving rise to the new paradigm of edge intelligent sensing (EI-Sense). This paradigm leverages ubiquitous edge devices for environmental sensing and deploys AI algorithms at edge servers to interpret the observations via remote inferen… ▽ More The forthcoming sixth-generation (6G) mobile network is set to merge edge artificial intelligence (AI) and integrated sensing and communication (ISAC) extensively, giving rise to the new paradigm of edge intelligent sensing (EI-Sense). This paradigm leverages ubiquitous edge devices for environmental sensing and deploys AI algorithms at edge servers to interpret the observations via remote inference on wirelessly uploaded features. A significant challenge arises in designing EI-Sense systems for 6G mission-critical applications, which demand high performance under stringent latency constraints. To tackle this challenge, we focus on the end-to-end (E2E) performance of EI-Sense and characterize a source-channel tradeoff that balances source distortion and channel reliability. In this work, we establish a theoretical foundation for the source-channel tradeoff by quantifying the effects of source coding on feature discriminant gains and channel reliability on packet loss. Building on this foundation, we design the coding rate control by optimizing the tradeoff to minimize the E2E sensing error probability, leading to a low-complexity algorithm for ultra-low-latency EI-Sense. Finally, we validate our theoretical analysis and proposed coding rate control algorithm through extensive experiments on both synthetic and real datasets, demonstrating the sensing performance gain of our approach with respect to traditional reliability-centric methods. △ Less

Submitted 6 March, 2025; originally announced March 2025.

DRL-based Dolph-Tschebyscheff Beamforming in Downlink Transmission for Mobile Users

Authors: Nancy Nayak, Kin K. Leung, Lajos Hanzo

Abstract: With the emergence of AI technologies in next-generation communication systems, machine learning plays a pivotal role due to its ability to address high-dimensional, non-stationary optimization problems within dynamic environments while maintaining computational efficiency. One such application is directional beamforming, achieved through learning-based blind beamforming techniques that utilize al… ▽ More With the emergence of AI technologies in next-generation communication systems, machine learning plays a pivotal role due to its ability to address high-dimensional, non-stationary optimization problems within dynamic environments while maintaining computational efficiency. One such application is directional beamforming, achieved through learning-based blind beamforming techniques that utilize already existing radio frequency (RF) fingerprints of the user equipment obtained from the base stations and eliminate the need for additional hardware or channel and angle estimations. However, as the number of users and antenna dimensions increase, thereby expanding the problem's complexity, the learning process becomes increasingly challenging, and the performance of the learning-based method cannot match that of the optimal solution. In such a scenario, we propose a deep reinforcement learning-based blind beamforming technique using a learnable Dolph-Tschebyscheff antenna array that can change its beam pattern to accommodate mobile users. Our simulation results show that the proposed method can support data rates very close to the best possible values. △ Less

Submitted 3 February, 2025; originally announced February 2025.

Resource-Efficient Compilation of Distributed Quantum Circuits for Solving Large-Scale Wireless Communication Network Problems

Authors: Kuan-Cheng Chen, Felix Burt, Shang Yu, Chen-Yu Liu, Min-Hsiu Hsieh, Kin K. Leung

Abstract: Optimizing routing in Wireless Sensor Networks (WSNs) is pivotal for minimizing energy consumption and extending network lifetime. This paper introduces a resourceefficient compilation method for distributed quantum circuits tailored to address large-scale WSN routing problems. Leveraging a hybrid classical-quantum framework, we employ spectral clustering for network partitioning and the Quantum A… ▽ More Optimizing routing in Wireless Sensor Networks (WSNs) is pivotal for minimizing energy consumption and extending network lifetime. This paper introduces a resourceefficient compilation method for distributed quantum circuits tailored to address large-scale WSN routing problems. Leveraging a hybrid classical-quantum framework, we employ spectral clustering for network partitioning and the Quantum Approximate Optimization Algorithm (QAOA) for optimizing routing within manageable subgraphs. We formulate the routing problem as a Quadratic Unconstrained Binary Optimization (QUBO) problem, providing comprehensive mathematical formulations and complexity analyses. Comparative evaluations against traditional classical algorithms demonstrate significant energy savings and enhanced scalability. Our approach underscores the potential of integrating quantum computing techniques into wireless communication networks, offering a scalable and efficient solution for future network optimization challenges △ Less

Submitted 17 January, 2025; originally announced January 2025.

Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning

Authors: Kuan-Cheng Chen, Samuel Yen-Chi Chen, Chen-Yu Liu, Kin K. Leung

Abstract: In this paper, we introduce Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning (Dist-QTRL), a novel approach to addressing the scalability challenges of traditional Reinforcement Learning (RL) by integrating quantum computing principles. Quantum-Train Reinforcement Learning (QTRL) leverages parameterized quantum circuits to efficiently generate neural network parameters, achieving… ▽ More In this paper, we introduce Quantum-Train-Based Distributed Multi-Agent Reinforcement Learning (Dist-QTRL), a novel approach to addressing the scalability challenges of traditional Reinforcement Learning (RL) by integrating quantum computing principles. Quantum-Train Reinforcement Learning (QTRL) leverages parameterized quantum circuits to efficiently generate neural network parameters, achieving a \(poly(\log(N))\) reduction in the dimensionality of trainable parameters while harnessing quantum entanglement for superior data representation. The framework is designed for distributed multi-agent environments, where multiple agents, modeled as Quantum Processing Units (QPUs), operate in parallel, enabling faster convergence and enhanced scalability. Additionally, the Dist-QTRL framework can be extended to high-performance computing (HPC) environments by utilizing distributed quantum training for parameter reduction in classical neural networks, followed by inference using classical CPUs or GPUs. This hybrid quantum-HPC approach allows for further optimization in real-world applications. In this paper, we provide a mathematical formulation of the Dist-QTRL framework and explore its convergence properties, supported by empirical results demonstrating performance improvements over centric QTRL models. The results highlight the potential of quantum-enhanced RL in tackling complex, high-dimensional tasks, particularly in distributed computing settings, where our framework achieves significant speedups through parallelization without compromising model accuracy. This work paves the way for scalable, quantum-enhanced RL systems in practical applications, leveraging both quantum and classical computational resources. △ Less

Submitted 11 December, 2024; originally announced December 2024.

Noise-Aware Distributed Quantum Approximate Optimization Algorithm on Near-term Quantum Hardware

Authors: Kuan-Cheng Chen, Xiatian Xu, Felix Burt, Chen-Yu Liu, Shang Yu, Kin K Leung

Abstract: This paper introduces a noise-aware distributed Quantum Approximate Optimization Algorithm (QAOA) tailored for execution on near-term quantum hardware. Leveraging a distributed framework, we address the limitations of current Noisy Intermediate-Scale Quantum (NISQ) devices, which are hindered by limited qubit counts and high error rates. Our approach decomposes large QAOA problems into smaller sub… ▽ More This paper introduces a noise-aware distributed Quantum Approximate Optimization Algorithm (QAOA) tailored for execution on near-term quantum hardware. Leveraging a distributed framework, we address the limitations of current Noisy Intermediate-Scale Quantum (NISQ) devices, which are hindered by limited qubit counts and high error rates. Our approach decomposes large QAOA problems into smaller subproblems, distributing them across multiple Quantum Processing Units (QPUs) to enhance scalability and performance. The noise-aware strategy incorporates error mitigation techniques to optimize qubit fidelity and gate operations, ensuring reliable quantum computations. We evaluate the efficacy of our framework using the HamilToniQ Benchmarking Toolkit, which quantifies the performance across various quantum hardware configurations. The results demonstrate that our distributed QAOA framework achieves significant improvements in computational speed and accuracy, showcasing its potential to solve complex optimization problems efficiently in the NISQ era. This work sets the stage for advanced algorithmic strategies and practical quantum system enhancements, contributing to the broader goal of achieving quantum advantage. △ Less

Submitted 9 August, 2024; v1 submitted 24 July, 2024; originally announced July 2024.

AdaptSFL: Adaptive Split Federated Learning in Resource-constrained Edge Networks

Authors: Zheng Lin, Guanqiao Qu, Wei Wei, Xianhao Chen, Kin K. Leung

Abstract: The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of floading the primary training workload to a server via model partitioning while enabling parallel training among edge devices. However, although system optimization su… ▽ More The increasing complexity of deep neural networks poses significant barriers to democratizing them to resource-limited edge devices. To address this challenge, split federated learning (SFL) has emerged as a promising solution by of floading the primary training workload to a server via model partitioning while enabling parallel training among edge devices. However, although system optimization substantially influences the performance of SFL under resource-constrained systems, the problem remains largely uncharted. In this paper, we provide a convergence analysis of SFL which quantifies the impact of model splitting (MS) and client-side model aggregation (MA) on the learning performance, serving as a theoretical foundation. Then, we propose AdaptSFL, a novel resource-adaptive SFL framework, to expedite SFL under resource-constrained edge computing systems. Specifically, AdaptSFL adaptively controls client-side MA and MS to balance communication-computing latency and training convergence. Extensive simulations across various datasets validate that our proposed AdaptSFL framework takes considerably less time to achieve a target accuracy than benchmarks, demonstrating the effectiveness of the proposed strategies. △ Less

Submitted 4 June, 2025; v1 submitted 19 March, 2024; originally announced March 2024.

Comments: 16 pages, 12 figures

Temporal Dependencies in Feature Importance for Time Series Predictions

Authors: Kin Kwan Leung, Clayton Rooke, Jonathan Smith, Saba Zuberi, Maksims Volkovs

Abstract: Time series data introduces two key challenges for explainability methods: firstly, observations of the same feature over subsequent time steps are not independent, and secondly, the same feature can have varying importance to model predictions over time. In this paper, we propose Windowed Feature Importance in Time (WinIT), a feature removal based explainability approach to address these issues.… ▽ More Time series data introduces two key challenges for explainability methods: firstly, observations of the same feature over subsequent time steps are not independent, and secondly, the same feature can have varying importance to model predictions over time. In this paper, we propose Windowed Feature Importance in Time (WinIT), a feature removal based explainability approach to address these issues. Unlike existing feature removal explanation methods, WinIT explicitly accounts for the temporal dependence between different observations of the same feature in the construction of its importance score. Furthermore, WinIT captures the varying importance of a feature over time, by summarizing its importance over a window of past time steps. We conduct an extensive empirical study on synthetic and real-world data, compare against a wide range of leading explainability methods, and explore the impact of various evaluation strategies. Our results show that WinIT achieves significant gains over existing methods, with more consistent performance across different evaluation metrics. The code for our work is publicly available at \url{https://github.com/layer6ai-labs/WinIT}. △ Less

Submitted 6 March, 2023; v1 submitted 29 July, 2021; originally announced July 2021.

Comments: International Conference on Learning Representations 2023 (ICLR'23)

Additive Link Metrics Identification: Proof of Selected Lemmas and Propositions

Authors: Liang Ma, Ting He, Kin K. Leung, Don Towsley, Ananthram Swami

Abstract: This is a technical report, containing all the lemma and proposition proofs in paper "Topological Constraints on Identifying Additive Link Metrics via End-to-end Paths Measurements" by Liang Ma, Ting He, Kin K. Leung, Don Towsley, and Ananthram Swami, published in Annual Conference of The International Technology Alliance (ACITA), 2012. This is a technical report, containing all the lemma and proposition proofs in paper "Topological Constraints on Identifying Additive Link Metrics via End-to-end Paths Measurements" by Liang Ma, Ting He, Kin K. Leung, Don Towsley, and Ananthram Swami, published in Annual Conference of The International Technology Alliance (ACITA), 2012. △ Less

Submitted 17 December, 2020; originally announced January 2021.

Comments: arXiv admin note: substantial text overlap with arXiv:2012.12190

Efficient Identification of Additive Link Metrics: Theorem Proof and Evaluations

Authors: Liang Ma, Ting He, Kin K. Leung, Don Towsley, Ananthram Swami

Abstract: This is a technical report, containing all the theorem proofs and additional evaluations in paper "Efficient Identification of Additive Link Metrics via Network Tomography" by Liang Ma, Ting He, Kin K. Leung, Don Towsley, and Ananthram Swami, published in IEEE ICDCS, 2013. This is a technical report, containing all the theorem proofs and additional evaluations in paper "Efficient Identification of Additive Link Metrics via Network Tomography" by Liang Ma, Ting He, Kin K. Leung, Don Towsley, and Ananthram Swami, published in IEEE ICDCS, 2013. △ Less

Submitted 17 December, 2020; originally announced December 2020.

Identification of Additive Link Metrics: Proof of Selected Theorems

Authors: Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, Don Towsley

Abstract: This is a technical report, containing all the theorem proofs in the following two papers: (1) Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, and Don Towsley, "Identifiability of Link Metrics Based on End-to-end Path Measurements," in ACM IMC, 2013. (2) Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, and Don Towsley, "Inferring Link Metrics from End-to-end Path Measurements: Identifiability a… ▽ More This is a technical report, containing all the theorem proofs in the following two papers: (1) Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, and Don Towsley, "Identifiability of Link Metrics Based on End-to-end Path Measurements," in ACM IMC, 2013. (2) Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, and Don Towsley, "Inferring Link Metrics from End-to-end Path Measurements: Identifiability and Monitor Placement," IEEE/ACM Transactions on Networking, vol. 22, no. 4, pp. 1351-1368, 2014. △ Less

Submitted 23 December, 2020; v1 submitted 17 December, 2020; originally announced December 2020.

Comments: References are updated

Partial Network Identifiability: Theorem Proof and Evaluation

Authors: Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, Don Towsley

Abstract: This is a technical report, containing all the theorem proofs and additional evaluations in paper "Monitor Placement for Maximal Identifiability in Network Tomography" by Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, Don Towsley, published in IEEE INFOCOM, 2014. This is a technical report, containing all the theorem proofs and additional evaluations in paper "Monitor Placement for Maximal Identifiability in Network Tomography" by Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, Don Towsley, published in IEEE INFOCOM, 2014. △ Less

Submitted 17 December, 2020; originally announced December 2020.

Link Identifiability with Two Monitors: Proof of Selected Theorems

Authors: Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, Don Towsley

Abstract: This is a technical report, containing all the theorem proofs in paper "Link Identifiability in Communication Networks with Two Monitors" by Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, and Don Towsley, published in IEEE Globecom, 2013. This is a technical report, containing all the theorem proofs in paper "Link Identifiability in Communication Networks with Two Monitors" by Liang Ma, Ting He, Kin K. Leung, Ananthram Swami, and Don Towsley, published in IEEE Globecom, 2013. △ Less

Submitted 24 December, 2020; v1 submitted 17 December, 2020; originally announced December 2020.

Comments: Auxiliary algorithms are removed from this report as they exist in the main (IEEE Globecom'13) paper. arXiv admin note: substantial text overlap with arXiv:2012.11378

Fundamental Theories in Node Failure Localization

Authors: Liang Ma, Ting He, Ananthram Swami, Don Towsley, Kin K. Leung, Jessica Lowe

Abstract: This is a technical report, containing all the theorem proofs in paper "Node Failure Localization in Communication Networks via Network Tomography" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, Kin K. Leung, and Jessica Lowe, published in ITA Annual Fall Meeting, 2014. This is a technical report, containing all the theorem proofs in paper "Node Failure Localization in Communication Networks via Network Tomography" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, Kin K. Leung, and Jessica Lowe, published in ITA Annual Fall Meeting, 2014. △ Less

Submitted 17 December, 2020; originally announced December 2020.

Comments: arXiv admin note: text overlap with arXiv:2012.09959

Failure Localization Capability: Theorem Proof and Evaluation

Authors: Liang Ma, Ting He, Ananthram Swami, Don Towsley, Kin K. Leung

Abstract: This is a technical report, containing all the theorem proofs and additional evaluations in paper "Network Capability in Localizing Node Failures via End-to-end Path Measurements" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, and Kin K. Leung, published in IEEE/ACM Transactions on Networking, vol. 25, no. 1, pp. 434-450, 2017. This is a technical report, containing all the theorem proofs and additional evaluations in paper "Network Capability in Localizing Node Failures via End-to-end Path Measurements" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, and Kin K. Leung, published in IEEE/ACM Transactions on Networking, vol. 25, no. 1, pp. 434-450, 2017. △ Less

Submitted 26 December, 2020; v1 submitted 17 December, 2020; originally announced December 2020.

Comments: Updated references

Node Failure Localization: Theorem Proof

Authors: Liang Ma, Ting He, Ananthram Swami, Don Towsley, Kin K. Leung

Abstract: This is a technical report, containing all the theorem proofs in paper "On Optimal Monitor Placement for Localizing Node Failures via Network Tomography" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, and Kin K. Leung, published in IFIP WG 7.3 Performance, 2015. This is a technical report, containing all the theorem proofs in paper "On Optimal Monitor Placement for Localizing Node Failures via Network Tomography" by Liang Ma, Ting He, Ananthram Swami, Don Towsley, and Kin K. Leung, published in IFIP WG 7.3 Performance, 2015. △ Less

Submitted 16 December, 2020; originally announced December 2020.

Resource Allocation in One-dimensional Distributed Service Networks with Applications

Authors: Nitish K. Panigrahy, Prithwish Basu, Philippe Nain, Don Towsley, Ananthram Swami, Kevin S. Chan, Kin K. Leung

Abstract: We consider assignment policies that allocate resources to users, where both resources and users are located on a one-dimensional line. First, we consider unidirectional assignment policies that allocate resources only to users located to their left. We propose the Move to Right (MTR) policy, which scans from left to right assigning nearest rightmost available resource to a user, and contrast it t… ▽ More We consider assignment policies that allocate resources to users, where both resources and users are located on a one-dimensional line. First, we consider unidirectional assignment policies that allocate resources only to users located to their left. We propose the Move to Right (MTR) policy, which scans from left to right assigning nearest rightmost available resource to a user, and contrast it to the Unidirectional Gale-Shapley (UGS) matching policy. While both policies among all unidirectional policies, minimize the expected distance traveled by a request (request distance), MTR is fairer. Moreover, we show that when user and resource locations are modeled by statistical point processes, and resources are allowed to satisfy more than one user, the spatial system under unidirectional policies can be mapped into bulk service queueing systems, thus allowing the application of many queueing theory results that yield closed form expressions. As we consider a case where different resources can satisfy different numbers of users, we also generate new results for bulk service queues. We also consider bidirectional policies where there are no directional restrictions on resource allocation and develop an algorithm for computing the optimal assignment which is more efficient than known algorithms in the literature when there are more resources than users. Numerical evaluation of performance of unidirectional and bidirectional allocation schemes yields design guidelines beneficial for resource placement. \np{Finally, we present a heuristic algorithm, which leverages the optimal dynamic programming scheme for one-dimensional inputs to obtain approximate solutions to the optimal assignment problem for the two-dimensional scenario and empirically yields request distances within a constant factor of the optimal solution. △ Less

Submitted 8 November, 2020; originally announced November 2020.

Comments: arXiv admin note: text overlap with arXiv:1901.02414

On the Analysis of Spatially Constrained Power of Two Choice Policies

Authors: Nitish K. Panigrahy, Prithwish Basu, Don Towsley, Ananthram Swami, Kin K. Leung

Abstract: We consider a class of power of two choice based assignment policies for allocating users to servers, where both users and servers are located on a two-dimensional Euclidean plane. In this framework, we investigate the inherent tradeoff between the communication cost, and load balancing performance of different allocation policies. To this end, we first design and evaluate a Spatial Power of two (… ▽ More We consider a class of power of two choice based assignment policies for allocating users to servers, where both users and servers are located on a two-dimensional Euclidean plane. In this framework, we investigate the inherent tradeoff between the communication cost, and load balancing performance of different allocation policies. To this end, we first design and evaluate a Spatial Power of two (sPOT) policy in which each user is allocated to the least loaded server among its two geographically nearest servers sequentially. When servers are placed on a two-dimensional square grid, sPOT maps to the classical Power of two (POT) policy on the Delaunay graph associated with the Voronoi tessellation of the set of servers. We show that the associated Delaunay graph is 4-regular and provide expressions for asymptotic maximum load using results from the literature. For uniform placement of servers, we map sPOT to a classical balls and bins allocation policy with bins corresponding to the Voronoi regions associated with the second order Voronoi diagram of the set of servers. We provide expressions for the lower bound on the asymptotic expected maximum load on the servers and prove that sPOT does not achieve POT load balancing benefits. However, experimental results suggest the efficacy of sPOT with respect to expected communication cost. Finally, we propose two non-uniform server sampling based POT policies that achieve the best of both the performance metrics. Experimental results validate the effctiveness of our proposed policies. △ Less

Submitted 4 November, 2020; originally announced November 2020.

Jointly-Learned State-Action Embedding for Efficient Reinforcement Learning

Authors: Paul J. Pritz, Liang Ma, Kin K. Leung

Abstract: While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state representations and the latest work has explored embedding techniques for actions, both with the aim of achieving better generalization and applicability. However… ▽ More While reinforcement learning has achieved considerable successes in recent years, state-of-the-art models are often still limited by the size of state and action spaces. Model-free reinforcement learning approaches use some form of state representations and the latest work has explored embedding techniques for actions, both with the aim of achieving better generalization and applicability. However, these approaches consider only states or actions, ignoring the interaction between them when generating embedded representations. In this work, we establish the theoretical foundations for the validity of training a reinforcement learning agent using embedded states and actions. We then propose a new approach for jointly learning embeddings for states and actions that combines aspects of model-free and model-based reinforcement learning, which can be applied in both discrete and continuous domains. Specifically, we use a model of the environment to obtain embeddings for states and actions and present a generic architecture that leverages these to learn a policy. In this way, the embedded representations obtained via our approach enable better generalization over both states and actions by capturing similarities in the embedding spaces. Evaluations of our approach on several gaming, robotic control, and recommender systems show it significantly outperforms state-of-the-art models in both discrete/continuous domains with large state/action spaces, thus confirming its efficacy. △ Less

Submitted 20 August, 2021; v1 submitted 9 October, 2020; originally announced October 2020.

Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computing

Authors: Qunsong Zeng, Yuqing Du, Kaibin Huang, Kin K. Leung

Abstract: Edge machine learning involves the deployment of learning algorithms at the network edge to leverage massive distributed data and computation resources to train artificial intelligence (AI) models. Among others, the framework of federated edge learning (FEEL) is popular for its data-privacy preservation. FEEL coordinates global model training at an edge server and local model training at edge devi… ▽ More Edge machine learning involves the deployment of learning algorithms at the network edge to leverage massive distributed data and computation resources to train artificial intelligence (AI) models. Among others, the framework of federated edge learning (FEEL) is popular for its data-privacy preservation. FEEL coordinates global model training at an edge server and local model training at edge devices that are connected by wireless links. This work contributes to the energy-efficient implementation of FEEL in wireless networks by designing joint computation-and-communication resource management ($\text{C}^2$RM). The design targets the state-of-the-art heterogeneous mobile architecture where parallel computing using both a CPU and a GPU, called heterogeneous computing, can significantly improve both the performance and energy efficiency. To minimize the sum energy consumption of devices, we propose a novel $\text{C}^2$RM framework featuring multi-dimensional control including bandwidth allocation, CPU-GPU workload partitioning and speed scaling at each device, and $\text{C}^2$ time division for each link. The key component of the framework is a set of equilibriums in energy rates with respect to different control variables that are proved to exist among devices or between processing units at each device. The results are applied to designing efficient algorithms for computing the optimal $\text{C}^2$RM policies faster than the standard optimization tools. Based on the equilibriums, we further design energy-efficient schemes for device scheduling and greedy spectrum sharing that scavenges "spectrum holes" resulting from heterogeneous $\text{C}^2$ time divisions among devices. Using a real dataset, experiments are conducted to demonstrate the effectiveness of $\text{C}^2$RM on improving the energy efficiency of a FEEL system. △ Less

Submitted 15 July, 2020; v1 submitted 14 July, 2020; originally announced July 2020.

State Action Separable Reinforcement Learning

Authors: Ziyao Zhang, Liang Ma, Kin K. Leung, Konstantinos Poularakis, Mudhakar Srivatsa

Abstract: Reinforcement Learning (RL) based methods have seen their paramount successes in solving serial decision-making and control problems in recent years. For conventional RL formulations, Markov Decision Process (MDP) and state-action-value function are the basis for the problem modeling and policy evaluation. However, several challenging issues still remain. Among most cited issues, the enormity of s… ▽ More Reinforcement Learning (RL) based methods have seen their paramount successes in solving serial decision-making and control problems in recent years. For conventional RL formulations, Markov Decision Process (MDP) and state-action-value function are the basis for the problem modeling and policy evaluation. However, several challenging issues still remain. Among most cited issues, the enormity of state/action space is an important factor that causes inefficiency in accurately approximating the state-action-value function. We observe that although actions directly define the agents' behaviors, for many problems the next state after a state transition matters more than the action taken, in determining the return of such a state transition. In this regard, we propose a new learning paradigm, State Action Separable Reinforcement Learning (sasRL), wherein the action space is decoupled from the value function learning process for higher efficiency. Then, a light-weight transition model is learned to assist the agent to determine the action that triggers the associated state transition. In addition, our convergence analysis reveals that under certain conditions, the convergence time of sasRL is $O(T^{1/k})$, where $T$ is the convergence time for updating the value function in the MDP-based formulation and $k$ is a weighting factor. Experiments on several gaming scenarios show that sasRL outperforms state-of-the-art MDP-based RL algorithms by up to $75\%$. △ Less

Submitted 5 June, 2020; originally announced June 2020.

Comments: 16 pages

Overcoming Noisy and Irrelevant Data in Federated Learning

Authors: Tiffany Tuor, Shiqiang Wang, Bong Jun Ko, Changchang Liu, Kin K. Leung

Abstract: Many image and vision applications require a large amount of data for model training. Collecting all such data at a central location can be challenging due to data privacy and communication bandwidth restrictions. Federated learning is an effective way of training a machine learning model in a distributed manner from local data collected by client devices, which does not require exchanging the raw… ▽ More Many image and vision applications require a large amount of data for model training. Collecting all such data at a central location can be challenging due to data privacy and communication bandwidth restrictions. Federated learning is an effective way of training a machine learning model in a distributed manner from local data collected by client devices, which does not require exchanging the raw data among clients. A challenge is that among the large variety of data collected at each client, it is likely that only a subset is relevant for a learning task while the rest of data has a negative impact on model training. Therefore, before starting the learning process, it is important to select the subset of data that is relevant to the given federated learning task. In this paper, we propose a method for distributedly selecting relevant data, where we use a benchmark model trained on a small benchmark dataset that is task-specific, to evaluate the relevance of individual data samples at each client and select the data with sufficiently high relevance. Then, each client only uses the selected subset of its data in the federated learning process. The effectiveness of our proposed approach is evaluated on multiple real-world image datasets in a simulated system with a large number of clients, showing up to $25\%$ improvement in model accuracy compared to training with all data. △ Less

Submitted 22 June, 2020; v1 submitted 22 January, 2020; originally announced January 2020.

Comments: Accepted version in the 25th International Conference on Pattern Recognition (ICPR)

Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approach

Authors: Pengchao Han, Shiqiang Wang, Kin K. Leung

Abstract: Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication overhead and improve the overall efficiency of FL, gradient sparsification (GS) can be applied, where instead of the full gradient, only a small subset of important… ▽ More Federated learning (FL) is an emerging technique for training machine learning models using geographically dispersed data collected by local entities. It includes local computation and synchronization steps. To reduce the communication overhead and improve the overall efficiency of FL, gradient sparsification (GS) can be applied, where instead of the full gradient, only a small subset of important elements of the gradient is communicated. Existing work on GS uses a fixed degree of gradient sparsity for i.i.d.-distributed data within a datacenter. In this paper, we consider adaptive degree of sparsity and non-i.i.d. local datasets. We first present a fairness-aware GS method which ensures that different clients provide a similar amount of updates. Then, with the goal of minimizing the overall training time, we propose a novel online learning formulation and algorithm for automatically determining the near-optimal communication and computation trade-off that is controlled by the degree of gradient sparsity. The online learning algorithm uses an estimated sign of the derivative of the objective function, which gives a regret bound that is asymptotically equal to the case where exact derivative is available. Experiments with real datasets confirm the benefits of our proposed approaches, showing up to $40\%$ improvement in model accuracy for a finite training time. △ Less

Submitted 20 March, 2020; v1 submitted 14 January, 2020; originally announced January 2020.

Comments: Accepted at IEEE ICDCS 2020

Fast-Fourier-Forecasting Resource Utilisation in Distributed Systems

Authors: Paul J. Pritz, Daniel Perez, Kin K. Leung

Abstract: Distributed computing systems often consist of hundreds of nodes, executing tasks with different resource requirements. Efficient resource provisioning and task scheduling in such systems are non-trivial and require close monitoring and accurate forecasting of the state of the system, specifically resource utilisation at its constituent machines. Two challenges present themselves towards these obj… ▽ More Distributed computing systems often consist of hundreds of nodes, executing tasks with different resource requirements. Efficient resource provisioning and task scheduling in such systems are non-trivial and require close monitoring and accurate forecasting of the state of the system, specifically resource utilisation at its constituent machines. Two challenges present themselves towards these objectives. First, collecting monitoring data entails substantial communication overhead. This overhead can be prohibitively high, especially in networks where bandwidth is limited. Second, forecasting models to predict resource utilisation should be accurate and need to exhibit high inference speed. Mission critical scheduling and resource allocation algorithms use these predictions and rely on their immediate availability. To address the first challenge, we present a communication-efficient data collection mechanism. Resource utilisation data is collected at the individual machines in the system and transmitted to a central controller in batches. Each batch is processed by an adaptive data-reduction algorithm based on Fourier transforms and truncation in the frequency domain. We show that the proposed mechanism leads to a significant reduction in communication overhead while incurring only minimal error and adhering to accuracy guarantees. To address the second challenge, we propose a deep learning architecture using complex Gated Recurrent Units to forecast resource utilisation. This architecture is directly integrated with the above data collection mechanism to improve inference speed of our forecasting model. Using two real-world datasets, we demonstrate the effectiveness of our approach, both in terms of forecasting accuracy and inference speed. Our approach resolves challenges encountered in resource provisioning frameworks and can be applied to other forecasting problems. △ Less

Submitted 7 August, 2020; v1 submitted 13 January, 2020; originally announced January 2020.

Resource Sharing in the Edge: A Distributed Bargaining-Theoretic Approach

Authors: Faheem Zafari, Prithwish Basu, Kin K. Leung, Jian Li, Ananthram Swami, Don Towsley

Abstract: The growing demand for edge computing resources, particularly due to increasing popularity of Internet of Things (IoT), and distributed machine/deep learning applications poses a significant challenge. On the one hand, certain edge service providers (ESPs) may not have sufficient resources to satisfy their applications according to the associated service-level agreements. On the other hand, some E… ▽ More The growing demand for edge computing resources, particularly due to increasing popularity of Internet of Things (IoT), and distributed machine/deep learning applications poses a significant challenge. On the one hand, certain edge service providers (ESPs) may not have sufficient resources to satisfy their applications according to the associated service-level agreements. On the other hand, some ESPs may have additional unused resources. In this paper, we propose a resource-sharing framework that allows different ESPs to optimally utilize their resources and improve the satisfaction level of applications subject to constraints such as communication cost for sharing resources across ESPs. Our framework considers that different ESPs have their own objectives for utilizing their resources, thus resulting in a multi-objective optimization problem. We present an $N$-person \emph{Nash Bargaining Solution} (NBS) for resource allocation and sharing among ESPs with \emph{Pareto} optimality guarantee. Furthermore, we propose a \emph{distributed}, primal-dual algorithm to obtain the NBS by proving that the strong-duality property holds for the resultant resource sharing optimization problem. Using synthetic and real-world data traces, we show numerically that the proposed NBS based framework not only enhances the ability to satisfy applications' resource demands, but also improves utilities of different ESPs. △ Less

Submitted 4 July, 2020; v1 submitted 13 January, 2020; originally announced January 2020.

Comments: This work has been submitted to the IEEE for possible publication

Let's Share: A Game-Theoretic Framework for Resource Sharing in Mobile Edge Clouds

Authors: Faheem Zafari, Kin K. Leung, Don Towsley, Prithwish Basu, Ananthram Swami, Jian Li

Abstract: Mobile edge computing seeks to provide resources to different delay-sensitive applications. This is a challenging problem as an edge cloud-service provider may not have sufficient resources to satisfy all resource requests. Furthermore, allocating available resources optimally to different applications is also challenging. Resource sharing among different edge cloud-service providers can address t… ▽ More Mobile edge computing seeks to provide resources to different delay-sensitive applications. This is a challenging problem as an edge cloud-service provider may not have sufficient resources to satisfy all resource requests. Furthermore, allocating available resources optimally to different applications is also challenging. Resource sharing among different edge cloud-service providers can address the aforementioned limitation as certain service providers may have resources available that can be ``rented'' by other service providers. However, edge cloud service providers can have different objectives or \emph{utilities}. Therefore, there is a need for an efficient and effective mechanism to share resources among service providers, while considering the different objectives of various providers. We model resource sharing as a multi-objective optimization problem and present a solution framework based on \emph{Cooperative Game Theory} (CGT). We consider the strategy where each service provider allocates resources to its native applications first and shares the remaining resources with applications from other service providers. We prove that for a monotonic, non-decreasing utility function, the game is canonical and convex. Hence, the \emph{core} is not empty and the grand coalition is stable. We propose two algorithms \emph{Game-theoretic Pareto optimal allocation} (GPOA) and \emph{Polyandrous-Polygamous Matching based Pareto Optimal Allocation} (PPMPOA) that provide allocations from the core. Hence the obtained allocations are \emph{Pareto} optimal and the grand coalition of all the service providers is stable. Experimental results confirm that our proposed resource sharing framework improves utilities of edge cloud-service providers and application request satisfaction. △ Less

Submitted 2 January, 2020; originally announced January 2020.

Comments: The paper is currently under review in IEEE Transactions on Network and Service Management

Model Pruning Enables Efficient Federated Learning on Edge Devices

Authors: Yuang Jiang, Shiqiang Wang, Victor Valls, Bong Jun Ko, Wei-Han Lee, Kin K. Leung, Leandros Tassiulas

Abstract: Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a datacenter. To overcome this challenge, we propose PruneFL -- a novel FL a… ▽ More Federated learning (FL) allows model training from local data collected by edge/mobile devices while preserving data privacy, which has wide applicability to image and vision applications. A challenge is that client devices in FL usually have much more limited computation and communication resources compared to servers in a datacenter. To overcome this challenge, we propose PruneFL -- a novel FL approach with adaptive and distributed parameter pruning, which adapts the model size during FL to reduce both communication and computation overhead and minimize the overall training time, while maintaining a similar accuracy as the original model. PruneFL includes initial pruning at a selected client and further pruning as part of the FL process. The model size is adapted during this process, which includes maximizing the approximate empirical risk reduction divided by the time of one FL round. Our experiments with various datasets on edge devices (e.g., Raspberry Pi) show that: (i) we significantly reduce the training time compared to conventional FL and various other pruning-based methods; (ii) the pruned model with automatically determined size converges to an accuracy that is very similar to the original model, and it is also a lottery ticket of the original model. △ Less

Submitted 6 April, 2022; v1 submitted 26 September, 2019; originally announced September 2019.

Comments: Accepted for publication in IEEE Transactions on Neural Networks and Learning Systems (TNNLS)

MACS: Deep Reinforcement Learning based SDN Controller Synchronization Policy Design

Authors: Ziyao Zhang, Liang Ma, Konstantinos Poularakis, Kin K. Leung, Jeremy Tucker, Ananthram Swami

Abstract: In distributed software-defined networks (SDN), multiple physical SDN controllers, each managing a network domain, are implemented to balance centralised control, scalability, and reliability requirements. In such networking paradigms, controllers synchronize with each other, in attempts to maintain a logically centralised network view. Despite the presence of various design proposals for distribu… ▽ More In distributed software-defined networks (SDN), multiple physical SDN controllers, each managing a network domain, are implemented to balance centralised control, scalability, and reliability requirements. In such networking paradigms, controllers synchronize with each other, in attempts to maintain a logically centralised network view. Despite the presence of various design proposals for distributed SDN controller architectures, most existing works only aim at eliminating anomalies arising from the inconsistencies in different controllers' network views. However, the performance aspect of controller synchronization designs with respect to given SDN applications are generally missing. To fill this gap, we formulate the controller synchronization problem as a Markov decision process (MDP) and apply reinforcement learning techniques combined with deep neural networks (DNNs) to train a smart, scalable, and fine-grained controller synchronization policy, called the Multi-Armed Cooperative Synchronization (MACS), whose goal is to maximise the performance enhancements brought by controller synchronizations. Evaluation results confirm the DNN's exceptional ability in abstracting latent patterns in the distributed SDN environment, rendering significant superiority to MACS-based synchronization policy, which are 56% and 30% performance improvements over ONOS and greedy SDN controller synchronization heuristics. △ Less

Submitted 19 September, 2019; originally announced September 2019.

Comments: Published as a conference paper at ICNP 2019

Energy-Efficient Radio Resource Allocation for Federated Edge Learning

Authors: Qunsong Zeng, Yuqing Du, Kin K. Leung, Kaibin Huang

Abstract: Edge machine learning involves the development of learning algorithms at the network edge to leverage massive distributed data and computation resources. Among others, the framework of federated edge learning (FEEL) is particularly promising for its data-privacy preservation. FEEL coordinates global model training at a server and local model training at edge devices over wireless links. In this wo… ▽ More Edge machine learning involves the development of learning algorithms at the network edge to leverage massive distributed data and computation resources. Among others, the framework of federated edge learning (FEEL) is particularly promising for its data-privacy preservation. FEEL coordinates global model training at a server and local model training at edge devices over wireless links. In this work, we explore the new direction of energy-efficient radio resource management (RRM) for FEEL. To reduce devices' energy consumption, we propose energy-efficient strategies for bandwidth allocation and scheduling. They adapt to devices' channel states and computation capacities so as to reduce their sum energy consumption while warranting learning performance. In contrast with the traditional rate-maximization designs, the derived optimal policies allocate more bandwidth to those scheduled devices with weaker channels or poorer computation capacities, which are the bottlenecks of synchronized model updates in FEEL. On the other hand, the scheduling priority function derived in closed form gives preferences to devices with better channels and computation capacities. Substantial energy reduction contributed by the proposed strategies is demonstrated in learning experiments. △ Less

Submitted 13 July, 2019; originally announced July 2019.

Automated Computer Evaluation of Acute Ischemic Stroke and Large Vessel Occlusion

Authors: Jia You, Philip L. H. Yu, Anderson C. O. Tsang, Eva L. H. Tsui, Pauline P. S. Woo, Gilberto K. K. Leung

Abstract: Large vessel occlusion (LVO) plays an important role in the diagnosis of acute ischemic stroke. Identifying LVO of patients in the early stage on admission would significantly lower the probabilities of suffering from severe effects due to stroke or even save their lives. In this paper, we utilized both structural and imaging data from all recorded acute ischemic stroke patients in Hong Kong. Tota… ▽ More Large vessel occlusion (LVO) plays an important role in the diagnosis of acute ischemic stroke. Identifying LVO of patients in the early stage on admission would significantly lower the probabilities of suffering from severe effects due to stroke or even save their lives. In this paper, we utilized both structural and imaging data from all recorded acute ischemic stroke patients in Hong Kong. Total 300 patients (200 training and 100 testing) are used in this study. We established three hierarchical models based on demographic data, clinical data and features obtained from computerized tomography (CT) scans. The first two stages of modeling are merely based on demographic and clinical data. Besides, the third model utilized extra CT imaging features obtained from deep learning model. The optimal cutoff is determined at the maximal Youden index based on 10-fold cross-validation. With both clinical and imaging features, the Level-3 model achieved the best performance on testing data. The sensitivity, specificity, Youden index, accuracy and area under the curve (AUC) are 0.930, 0.684, 0.614, 0.790 and 0.850 respectively. △ Less

Submitted 18 June, 2019; originally announced June 2019.

Online Collection and Forecasting of Resource Utilization in Large-Scale Distributed Systems

Authors: Tiffany Tuor, Shiqiang Wang, Kin K. Leung, Bong Jun Ko

Abstract: Large-scale distributed computing systems often contain thousands of distributed nodes (machines). Monitoring the conditions of these nodes is important for system management purposes, which, however, can be extremely resource demanding as this requires collecting local measurements of each individual node and constantly sending those measurements to a central controller. Meanwhile, it is often us… ▽ More Large-scale distributed computing systems often contain thousands of distributed nodes (machines). Monitoring the conditions of these nodes is important for system management purposes, which, however, can be extremely resource demanding as this requires collecting local measurements of each individual node and constantly sending those measurements to a central controller. Meanwhile, it is often useful to forecast the future system conditions for various purposes such as resource planning/allocation and anomaly detection, but it is usually too resource-consuming to have one forecasting model running for each node, which may also neglect correlations in observed metrics across different nodes. In this paper, we propose a mechanism for collecting and forecasting the resource utilization of machines in a distributed computing system in a scalable manner. We present an algorithm that allows each local node to decide when to transmit its most recent measurement to the central node, so that the transmission frequency is kept below a given constraint value. Based on the measurements received from local nodes, the central node summarizes the received data into a small number of clusters. Since the cluster partitioning can change over time, we also present a method to capture the evolution of clusters and their centroids. As an effective way to reduce the amount of computation, time-series forecasting models are trained on the time-varying centroids of each cluster, to forecast the future resource utilizations of a group of local nodes. The effectiveness of our proposed approach is confirmed by extensive experiments using multiple real-world datasets. △ Less

Submitted 22 May, 2019; originally announced May 2019.

Comments: Accepted at IEEE International Conference on Distributed Computing Systems (ICDCS) 2019