Showing 1–50 of 59 results for author: Awad, M

The Forward-Backward Disconnect: State Dynamics, Credit Assignment, and Biological Grounding in Neural Computation

Authors: Hadi Al Mubasher, Mariette Awad

Abstract: A recurring pattern in neural computation is the reintroduction of dynamical and biological structure into models originally simplified for scalable optimization. Early feedforward networks reduced biological neurons to threshold or rate-like summation units, an abstraction compatible with global-gradient training at scale. Since then, forward computation has diversified: modern architectures carr… ▽ More A recurring pattern in neural computation is the reintroduction of dynamical and biological structure into models originally simplified for scalable optimization. Early feedforward networks reduced biological neurons to threshold or rate-like summation units, an abstraction compatible with global-gradient training at scale. Since then, forward computation has diversified: modern architectures carry recurrent state, retrieve from long contexts through attention and associative memory, compress histories through structured state-space dynamics, evolve in continuous time, settle to implicit equilibria, and communicate through sparse spikes. Training has diversified less. Scalable learning remains concentrated around backpropagation, backpropagation through time, adjoint methods, implicit differentiation, and surrogate-gradient variants. We call this asymmetry the forward-backward disconnect and develop a taxonomy spanning neural model families along three coupled axes: state-dynamics structure, credit-assignment mechanism, and biological grounding. Forward and learning grounding are treated separately, and the unit of analysis is the architecture-learning configuration rather than the architecture name alone. Across static, recurrent, attention-based, state-space, continuous-time, implicit, spiking, biologically plausible, and neuromorphic families, forward dynamics have diversified while the highest demonstrated scales remain concentrated in global or closely gradient-derived error-propagation mechanisms. Closing this disconnect requires better alignment among state dynamics, credit assignment, and computational substrate. △ Less

Submitted 20 August, 2026; originally announced August 2026.

RRFC: Recursive Refinement via Feedback Conditioning for Iterative Image-to-Image Generation

Authors: Kareem Hassani, Chaymaa Abbas, Hadi Al Mubasher, Mariette Awad

Abstract: Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it. Although trained to produce the best possible result in one step, such a model leaves room for improvement if it can adaptively revise its own output over iterations. We propose Recursive Refinement via Feedback Conditioning (R… ▽ More Conditional image-to-image generators are single-shot: they map input features to an output in one forward pass and treat it as final, with no opportunity to improve on it. Although trained to produce the best possible result in one step, such a model leaves room for improvement if it can adaptively revise its own output over iterations. We propose Recursive Refinement via Feedback Conditioning (RRFC), a novel feedback-conditioning framework for iterative output refinement that teaches a model to adaptively revise its output by conditioning on a new signal, namely its most recent previous prediction, which is fed back as an auxiliary set of channels alongside the original input. This preserves the generator's core architecture while modifying its conditioning interface and, depending on the model family, its training or inference procedure, so RRFC can be attached to existing generators without redesign. We evaluate RRFC across six baselines spanning adversarial, equilibrium, and diffusion-based models and three paired image-to-image translation tasks. Across 18 architecture-task settings, RRFC yields seven Holm-corrected improvements, seven degradations, and four non-significant changes. The gains concentrate on reconstruction-fidelity and identity settings, while five of the seven degradations fall on the single semantic-layout task, where every model declines. These results indicate that feedback-based refinement helps when its objective overlaps with the evaluated property, and that its gains concentrate on the tasks where that overlap holds. △ Less

Submitted 16 August, 2026; originally announced August 2026.

THESIS-MoE: Trainable Hierarchical Extraction and SteerIng of Sycophancy in Mixture-of-Experts

Authors: Kareem Hassani, Chaymaa Abbas, Lama Mawlawi, Mariette Awad

Abstract: Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure. Existing activation steering methods typically apply a single contrastive direction uniformly throughout the model, which is an unconditional intervention that alters activations even when no sycophantic behavior is present, trading knowledge retention for behavioral co… ▽ More Sycophancy, the tendency of a language model to change its answer to match a user's stated belief, is a common alignment failure. Existing activation steering methods typically apply a single contrastive direction uniformly throughout the model, which is an unconditional intervention that alters activations even when no sycophantic behavior is present, trading knowledge retention for behavioral correction. In Mixture-of-Experts (MoE) models, prior work further suggests that behavior is encoded within expert computations rather than routing decisions alone, making precise behavioral steering particularly challenging. In this work, we introduce a shared contrastive signal, built from matched prompts with and without a stated belief, that identifies where sycophancy lives across the MoE hierarchy and drives interventions that act only where the behavior is present. We formulate localization as a causal search over a granularity ladder of MoE blocks, experts, attention blocks, and heads, and compare unconditional subtraction against two conditional alternatives: an analytic projection-based subtraction and a learned per-token gate that steers the model away from sycophancy while keeping its weights frozen. We evaluate on three MoE models measuring sycophancy alongside general knowledge and reasoning benchmarks. Our conditional interventions removed up to 90\% of the belief-induced sycophancy. Our results demonstrate that sycophancy resides in identifiable computational subcircuits and can be selectively steered while maintaining a favorable removal-retention trade-off. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Jais 2: A Family of Arabic-Centric Open Large Language Models

Authors: Mohamed Anwar, Abed Alhakim Freihat, George Ibrahim, Mostafa Awad, Abdelrahman Sadallah, Gurpreet Gosal, Gokulakrishnan Ramakrishnan, Sarath Chandran, Biswajit Mishra, Rituraj Joshi, Ahmed Frikha, Etienne Goffinet, Abhishek Maiti, Ali El Filali, Sarah AlBarri, Samujjwal Ghosh, Rahul Pal, Parvez Mullah, Awantika Shukla, Sajid siddiki, Samta Kamboj, Onkar Pandit, Sunil Kumar Sahu, AbdelRahman Elbadawy, Amr Mohamed , et al. (35 additional authors not shown)

Abstract: Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competiti… ▽ More Jais 2 is a family of Arabic-centric large language models developed jointly by MBZUAI, Cerebras, and Inception, designed to advance Arabic-centric language modeling, with strong performance across the Arabic and culturally grounded benchmarks evaluated in this report. The family includes, to our knowledge, the largest open Arabic-centric LLM trained from scratch at 70B parameters, and a competitive 8B-parameter variant among the evaluated open models. A custom Arabic-centric vocabulary enables efficient training and inference. In addition, an optimized architecture and training recipe yield highly compute-efficient training. With a substantially smaller token budget than comparable models, Jais 2 achieves strong Arabic performance on the benchmarks considered in this report and competitive English results. The models obtain leading results among the evaluated open models on OALL2 and AraGen. They also perform strongly on several culturally grounded Arabic benchmarks, including poetry, religion, cuisine, and dream interpretation, as well as in general tasks such as translation and summarization. We release the models in HuggingFace under a commercially permissive license. Jais 2 70B is also released as a chat app on the Web, iOS, and Android; it runs on Cerebras hardware, delivering up to 2,000 tokens per second, and enabling high-throughput Arabic-centric chat serving in our deployment setting. By uniting scale, linguistic diversity, cultural fidelity, openness, and speed, Jais 2 provides an open-weight foundation intended to support further research and development in Arabic-centric LLMs. △ Less

Submitted 7 July, 2026; originally announced August 2026.

Measuring Curriculum-Labor Market Alignment at the Scale of a Program Portfolio

Authors: Sherzod Turaev, Saja Aldabet, Mary John, Namya Musthafa, Mamoun Awad, Nazar Zaki, Khaled Shuaib

Abstract: A college offering several overlapping computing degrees implicitly assumes that its programs are differentiated in line with how the labor market segments computing work and that, together, they prepare graduates for that market. Testing this is difficult, because the instruments available to curriculum committees, namely advisory boards, tracer studies, and employer surveys, are slow, narrow, an… ▽ More A college offering several overlapping computing degrees implicitly assumes that its programs are differentiated in line with how the labor market segments computing work and that, together, they prepare graduates for that market. Testing this is difficult, because the instruments available to curriculum committees, namely advisory boards, tracer studies, and employer surveys, are slow, narrow, and hard to reproduce. We apply one uniform, taxonomy-anchored alignment analysis across all five undergraduate programs of a College of Information Technology, comparing 1,922 course learning outcomes against 103,349 competencies extracted from a unified corpus of 5,186 deduplicated job openings from four boards. Every competency is obtained by a grounded single-language-model procedure that copies it verbatim from the source and verifies it against the source, then assigns it to one of eleven ESCO-aligned domains and a Bloom cognitive level; the curricular supply is read not as a catalog but on a realized-attainment basis that respects the credit-hour and elective constraints under which a student completes a degree. The extraction is validated blind by two independent faculty raters (domain kappa 0.91, Bloom level kappa 0.86) and the ESCO matching against a human-adjudicated gold set (kappa 0.72). Four findings emerge. The content gaps are systemic rather than program-specific, concentrated in systems, software engineering, security, and web development; the shared college core satisfies only about a third of the demanded competencies; the programs are well differentiated in disciplinary content yet homogeneous in where they fall short; and the curriculum is pitched roughly a full Bloom level below the market across the portfolio, most acutely in systems. We discuss the implications for program design, curriculum governance, and the practice of curriculum analytics. △ Less

Submitted 3 July, 2026; originally announced August 2026.

Comments: 21 pages, 8 figures, 4 tables

MSC Class: 68T50 ACM Class: I.2.7

Loc2Repair: A Framework for Evaluating the Impact of File-Level Issue Localization in Repo-Level LLM Repair

Authors: Mohammad Nour Al Awad, Sergey Ivanov

Abstract: Repository-grounded automated repair is often reported as a single end-to-end capability, which hides distinct failure modes such as poor file targeting, incorrect patch synthesis, and failed iterative debugging. We present Loc2Repair, a modular evaluation framework for controlled analysis of repository-grounded repair pipelines, and use it to isolate file-level issue localization as an upstream v… ▽ More Repository-grounded automated repair is often reported as a single end-to-end capability, which hides distinct failure modes such as poor file targeting, incorrect patch synthesis, and failed iterative debugging. We present Loc2Repair, a modular evaluation framework for controlled analysis of repository-grounded repair pipelines, and use it to isolate file-level issue localization as an upstream variable. Loc2Repair decouples localization and repair under a shared runtime, artifact schema, and evaluation harness, allowing researchers to combine different localization models and repair backbones under matched conditions. Using three repair backbones on SWE-bench Verified, we compare baseline repair without explicit localization, repair guided by predicted localization from two localizers, and repair guided by gold modified-file sets. Explicit localization consistently improves resolved rate across all backbones: pooled performance increases from 44.7% for baseline repair to 48.9% and 49.1% with predicted localization, and to 52.4% with gold localization. Localization also reduces mean elapsed time overall: in pooled paired analysis, mean elapsed time decreases by 100.94 s and 52.25 s for the two predicted-localization settings, and by 154.45 s with gold guidance, although token effects remain heterogeneous across models. Overall, Loc2Repair shows file-level localization is a consistent repair lever, improving effectiveness and mean latency in pooled analysis, while gold-guided failures expose headroom beyond localization. △ Less

Submitted 29 June, 2026; originally announced June 2026.

Comments: To appear in the Proceedings of the Generative Code Intelligence Workshop (GeCoIn 2026), co-located with the 35th International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026), Bremen, Germany, August 15--17, 2026

Measuring Curriculum Alignment across Topical Coverage, Competency, and Cognitive Depth: A Longitudinal Framework Applied to CS2013 and CS2023

Authors: Sherzod Turaev, Mary John, Saja Aldabet, Mamoun Awad, Nazar Zaki, Khaled Shuaib

Abstract: Undergraduate computer science is governed by international curricular guidelines revised about once a decade, yet programs lack a reliable, reproducible way to measure how completely they cover the current guidelines and how that coverage shifts when the guidelines are restructured. We address this with a human-in-the-loop pipeline that measures a program's coverage of an external body of knowled… ▽ More Undergraduate computer science is governed by international curricular guidelines revised about once a decade, yet programs lack a reliable, reproducible way to measure how completely they cover the current guidelines and how that coverage shifts when the guidelines are restructured. We address this with a human-in-the-loop pipeline that measures a program's coverage of an external body of knowledge, applied longitudinally to one accredited BSc in Computer Science against Computer Science Curricula 2013 (CS2013) and 2023 (CS2023). The pipeline represents the program and each guideline as structured corpora, generates candidate course-to-knowledge-unit matches by semantic retrieval, and confirms them through human judgment under an explicit coverage definition. Of seven benchmarked retrievers, a reciprocal-rank-fusion ensemble was strongest, and a reputed long-context model underperformed a small sentence model, so retriever choice must be measured. Both maps were validated by an independent second rater (Cohen's kappa 0.64 for CS2023, 0.69 for CS2013). The program covers 49.7% of CS2023 and 50.9% of CS2013 knowledge units, near-constant across a decade. Extending the same retrieve-then-confirm design to competency articulation and cognitive depth shows that the program articulates the competency for ~88% of covered units under each guideline, yet delivers it at the recommended depth for 76% of present units under CS2023 against 95% under CS2013, a gap reflecting the newer guideline's raised expectations, not the program. The longitudinal comparison separates persistent structural gaps (parallel and distributed computing, foundations of programming languages, systems fundamentals), uncovered against both guidelines and ABET, from differences that reflect the standard's evolution. The instrument is reusable and available from the authors on request. △ Less

Submitted 17 June, 2026; originally announced June 2026.

Comments: 24 pages, 5 figures, 8 tables

MSC Class: 68T50 ACM Class: I.2.7

An NLP-Driven Framework for Curriculum-Labor Market Alignment: Schema-Constrained LLM Extraction, ESCO-Anchored Semantic Matching, and Multi-Dimensional Gap Quantification

Authors: Sherzod Turaev, Mary John, Mamoun Awad, Nazar Zaki, Khaled Shuaib

Abstract: Schema-constrained information extraction from diverse educational and labor-market corpora remains an open challenge in natural language processing because existing pipelines rely primarily on lexical-surface methods that cannot recover implicit competencies, lack grounding in shared taxonomies, and provide no formal measures of extraction reliability or document-level completeness. To address th… ▽ More Schema-constrained information extraction from diverse educational and labor-market corpora remains an open challenge in natural language processing because existing pipelines rely primarily on lexical-surface methods that cannot recover implicit competencies, lack grounding in shared taxonomies, and provide no formal measures of extraction reliability or document-level completeness. To address these limitations, this paper proposes a four-stage NLP framework that combines (i) schema-constrained prompting of a two-model frontier-LLM ensemble against a JSON Schema-enforced seven-slot competency formalism, (ii) Sentence-BERT (SBERT) alignment of the extracted records against an eleven-domain ESCO v1.2.1 controlled vocabulary, (iii) a two-tier adjudication protocol that resolves inter-model disagreements, and (iv) a verification mechanism that combines per-slot Cohen's kappa, schema conformance, and document-level completeness audits. The framework is instantiated for a critical application in higher-education quality assurance, namely curriculum-labor market alignment for the ABET-accredited BSc Computer Science program at the United Arab Emirates University. The pipeline extracts 400 competency records from the 85-course 2025-2026 study plan and aligns them, under a five-scope analysis ranging from the computing core to a probability-weighted student trajectory, with 30 job postings (483 requirement clauses) at an SBERT cosine threshold of 0.50. The extractor achieves Cohen's kappa of 0.79 on the skill slot, with 100% schema conformance and 100% document-level completeness. The alignment surfaces interpretable supply-demand gaps of 25.0% in general and transversal skills, 13.8% in algorithms and computational theory, and 12.2% in software engineering and project management, with a near-zero 1.8% gap in artificial intelligence and data science despite 38.6% supply coverage. △ Less

Submitted 1 June, 2026; originally announced June 2026.

Comments: 53 pages, 9 figures, 4 tables

MSC Class: 68T50 ACM Class: I.2.7

Obscuring Data Contamination Through Translation: Evidence from Arabic Corpora

Authors: Chaymaa Abbas, Nour Shamaa, Mariette Awad

Abstract: Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these approaches are largely limited to English benchmarks, leaving multilingual contamination poorly understood. In this work, we investigate contamination dynamics in… ▽ More Data contamination undermines the validity of Large Language Model evaluation by enabling models to rely on memorized benchmark content rather than true generalization. While prior work has proposed contamination detection methods, these approaches are largely limited to English benchmarks, leaving multilingual contamination poorly understood. In this work, we investigate contamination dynamics in multilingual settings by fine-tuning several open-weight LLMs on varying proportions of Arabic datasets and evaluating them on original English benchmarks. To detect memorization, we extend the Tested Slot Guessing method with a choice-reordering strategy and incorporate Min-K% probability analysis, capturing both behavioral and distributional contamination signals. Our results show that translation into Arabic suppresses conventional contamination indicators, yet models still benefit from exposure to contaminated data, particularly those with stronger Arabic capabilities. This effect is consistently reflected in rising Mink% scores and increased cross-lingual answer consistency as contamination levels grow. To address this blind spot, we propose Translation-Aware Contamination Detection, which identifies contamination by comparing signals across multiple translated benchmark variants rather than English alone. The Translation-Aware Contamination Detection reliably exposes contamination even when English-only methods fail. Together, our findings highlight the need for multilingual, translation-aware evaluation pipelines to ensure fair, transparent, and reproducible assessment of LLMs. △ Less

Submitted 21 January, 2026; originally announced January 2026.

ChartComplete: A Taxonomy-based Inclusive Chart Dataset

Authors: Ahmad Mustapha, Charbel Toumieh, Mariette Awad

Abstract: With advancements in deep learning (DL) and computer vision techniques, the field of chart understanding is evolving rapidly. In particular, multimodal large language models (MLLMs) are proving to be efficient and accurate in understanding charts. To accurately measure the performance of MLLMs, the research community has developed multiple datasets to serve as benchmarks. By examining these datase… ▽ More With advancements in deep learning (DL) and computer vision techniques, the field of chart understanding is evolving rapidly. In particular, multimodal large language models (MLLMs) are proving to be efficient and accurate in understanding charts. To accurately measure the performance of MLLMs, the research community has developed multiple datasets to serve as benchmarks. By examining these datasets, we found that they are all limited to a small set of chart types. To bridge this gap, we propose the ChartComplete dataset. The dataset is based on a chart taxonomy borrowed from the visualization community, and it covers thirty different chart types. The dataset is a collection of classified chart images and does not include a learning signal. We present the ChartComplete dataset as is to the community to build upon it. △ Less

Submitted 19 January, 2026; v1 submitted 15 January, 2026; originally announced January 2026.

Comments: 7 pages, 4 figures, 3 tables, 1 algorithm. Dataset and source code available at https://github.com/AI-DSCHubAUB/ChartComplete-Dataset

ACM Class: I.2.10; I.4.8

A Benchmark for Omni-Modal Reasoning in Long Videos

Authors: Mohammed Irfan Kurpath, Jaseel Muhammad Kaithakkodan, Jinxing Zhou, Sahal Shaji Mullappilly, Mohammad Almansoori, Noor Ahsan, Beknur Kalmakhanbet, Sambal Shikhar, Rishabh Lalla, Jean Lahoud, Mariette Awad, Fahad Shahbaz Khan, Salman Khan, Rao Muhammad Anwer, Hisham Cholakkal

Abstract: Long-form omni-modal video understanding requires integrating vision, speech, and ambient audio with coherent long-context reasoning. Existing video benchmarks often trade off temporal scale, modality coverage, open-ended interaction, and interpretable scoring. To address this gap, we introduce LongShOTBench, a long video understanding benchmark designed around three coupled goals: holistic omni-m… ▽ More Long-form omni-modal video understanding requires integrating vision, speech, and ambient audio with coherent long-context reasoning. Existing video benchmarks often trade off temporal scale, modality coverage, open-ended interaction, and interpretable scoring. To address this gap, we introduce LongShOTBench, a long video understanding benchmark designed around three coupled goals: holistic omni-modal integration, intent-driven open-ended interaction, and rubric-level diagnosis. It builds single- and multi-turn questions from real viewing scenarios, with systematic tasks probing visual, speech, ambient-audio, temporal, and cross-modal reasoning. Each item includes a reference answer and a weighted criterion-level rubric, letting evaluation identify which perceptual facts, temporal links, modality-grounding requirements, and reasoning steps are satisfied or missed. All samples are manually verified to improve grounding, clarity, and rubric reliability. We also introduce LongShOTAgent, a training-free omni-modal evidence-seeking agent coupling full-video preprocessing with targeted retrieval, query-adaptive segment refinement, and explicit claim verification over visual, speech, and non-speech audio evidence. Its iterative search-refine-verify loop exposes intermediate evidence and lets modality-specific specialists re-analyze relevant moments before answering. We evaluate 105 video-capable models spanning open-source omni-modal models, vision-language systems, audio LLMs, agentic pipelines and closed-source APIs. Current MLLMs remain far from saturating LongShOTBench, while our LongShOTAgent is the strongest training-free system, reaching 66.64% overall. By releasing the benchmark, leaderboard, and method, we provide a shared, interpretable testbed for advancing long-form omni-modal video reasoning. Code, data, and the leaderboard are available at https://longshot.cvmbzuai.com/. △ Less

Submitted 16 June, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Cultural Rights and the Rights to Development in the Age of AI: Implications for Global Human Rights Governance

Authors: Alexander Kriebitz, Caitlin Corrigan, Aive Pevkur, Alberto Santos Ferro, Amanda Horzyk, Dirk Brand, Dohee Kim, Dodzi Koku Hattoh, Flavia Massucci, Gilles Fayad, Kamil Strzepek, Laud Ammah, Lavina Ramkissoon, Mariette Awad, Natalia Amasiadi, Nathan C. Walker, Nicole Manger, Sophia Devlin

Abstract: Cultural rights and the right to development are essential norms within the wider framework of international human rights law. However, recent technological advances in artificial intelligence (AI) and adjacent digital frontier technologies pose significant challenges to the protection and realization of these rights. This owes to the increasing influence of AI systems on the creation and depictio… ▽ More Cultural rights and the right to development are essential norms within the wider framework of international human rights law. However, recent technological advances in artificial intelligence (AI) and adjacent digital frontier technologies pose significant challenges to the protection and realization of these rights. This owes to the increasing influence of AI systems on the creation and depiction of cultural content, affect the use and distribution of the intellectual property of individuals and communities, and influence cultural participation and expression worldwide. In addition, the growing influence of AI thus risks exacerbating preexisting economic, social and digital divides and reinforcing inequities for marginalized communities. This dynamic challenges the existing interplay between cultural rights and the right to development, and raises questions about the integration of cultural and developmental considerations into emerging AI governance frameworks. To address these challenges, the paper examines the impact of AI on both categories of rights. Conceptually, it analyzes the epistemic and normative limitations of AI with respect to cultural and developmental assumptions embedded in algorithmic design and deployment, but also individual and structural impacts of AI on both rights. On this basis, the paper identifies gaps and tensions in existing AI governance frameworks with respect to cultural rights and the right to development. By situating cultural rights and the right to development within the broader landscape of AI and human rights, this paper contributes to the academic discourse on AI ethics, legal frameworks, and international human rights law. Finally, it outlines avenues for future research and policy development based on existing conversations in global AI governance. △ Less

Submitted 15 December, 2025; originally announced December 2025.

Defense That Attacks: How Robust Models Become Better Attackers

Authors: Mohamed Awad, Mahmoud Akrm, Walid Gomaa

Abstract: Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of attacks is underexplored. In this work, we ask whether adversarial training unintentionally increases the transferability of adversarial examples. To answer this, w… ▽ More Deep learning has achieved great success in computer vision, but remains vulnerable to adversarial attacks. Adversarial training is the leading defense designed to improve model robustness. However, its effect on the transferability of attacks is underexplored. In this work, we ask whether adversarial training unintentionally increases the transferability of adversarial examples. To answer this, we trained a diverse zoo of 36 models, including CNNs and ViTs, and conducted comprehensive transferability experiments. Our results reveal a clear paradox: adversarially trained (AT) models produce perturbations that transfer more effectively than those from standard models, which introduce a new ecosystem risk. To enable reproducibility and further study, we release all models, code, and experimental scripts. Furthermore, we argue that robustness evaluations should assess not only the resistance of a model to transferred attacks but also its propensity to produce transferable adversarial examples. △ Less

Submitted 12 December, 2025; v1 submitted 2 December, 2025; originally announced December 2025.

Pre-Filtering Code Suggestions using Developer Behavioral Telemetry to Optimize LLM-Assisted Programming

Authors: Mohammad Nour Al Awad, Sergey Ivanov, Olga Tikhonova

Abstract: Large Language Models (LLMs) are increasingly integrated into code editors to provide AI-powered code suggestions. Yet many of these suggestions are ignored, resulting in wasted computation, increased latency, and unnecessary interruptions. We introduce a lightweight pre-filtering model that predicts the likelihood of suggestion acceptance before invoking the LLM, using only real-time developer te… ▽ More Large Language Models (LLMs) are increasingly integrated into code editors to provide AI-powered code suggestions. Yet many of these suggestions are ignored, resulting in wasted computation, increased latency, and unnecessary interruptions. We introduce a lightweight pre-filtering model that predicts the likelihood of suggestion acceptance before invoking the LLM, using only real-time developer telemetry such as typing speed, file navigation, and editing activity. Deployed in a production-grade Visual Studio Code plugin over four months of naturalistic use, our approach nearly doubled acceptance rates (18.4% -> 34.2%) while suppressing 35% of low-value LLM calls. These findings demonstrate that behavioral signals alone can meaningfully improve both user experience and system efficiency in LLM-assisted programming, highlighting the value of timing-aware, privacy-preserving adaptation mechanisms. The filter operates solely on pre-invocation editor telemetry and never inspects code or prompts. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Journal ref: In Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW 2025)

Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds

Authors: Mohammad Nour Al Awad, Sergey Ivanov, Olga Tikhonova

Abstract: Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We propose an adaptive timing mechanism that dynamically adjusts the delay before offering a suggestion based on real-time developer feedback. Our suggested method… ▽ More Large Language Models (LLMs) have transformed code auto-completion by generating context-aware suggestions. Yet, deciding when to present these suggestions remains underexplored, often leading to interruptions or wasted inference calls. We propose an adaptive timing mechanism that dynamically adjusts the delay before offering a suggestion based on real-time developer feedback. Our suggested method combines a logistic transform of recent acceptance rates with a bounded delay range, anchored by a high-level binary prediction of the developer's cognitive state. In a two-month deployment with professional developers, our system improved suggestion acceptance from 4.9% with no delay to 15.4% with static delays, and to 18.6% with adaptive timing-while reducing blind rejections (rejections without being read) from 8.3% to 0.36%. Together, these improvements increase acceptance and substantially reduce wasted inference calls by 75%, making LLM-based code assistants more efficient and cost-effective in practice. △ Less

Submitted 24 November, 2025; originally announced November 2025.

Comments: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Journal ref: In Proceedings of the 40th IEEE/ACM International Conference on Automated Software Engineering Workshops (ASEW 2025)

A Multimodal Conversational Agent for Tabular Data Analysis

Authors: Mohammad Nour Al Awad, Sergey Ivanov, Olga Tikhonova, Ivan Khodnenko

Abstract: Large language models (LLMs) can reshape information processing by handling data analysis, visualization, and interpretation in an interactive, context-aware dialogue with users, including voice interaction, while maintaining high performance. In this article, we present Talk2Data, a multimodal LLM-driven conversational agent for intuitive data exploration. The system lets users query datasets wit… ▽ More Large language models (LLMs) can reshape information processing by handling data analysis, visualization, and interpretation in an interactive, context-aware dialogue with users, including voice interaction, while maintaining high performance. In this article, we present Talk2Data, a multimodal LLM-driven conversational agent for intuitive data exploration. The system lets users query datasets with voice or text instructions and receive answers as plots, tables, statistics, or spoken explanations. Built on LLMs, the suggested design combines OpenAI Whisper automatic speech recognition (ASR) system, Qwen-coder code generation LLM/model, custom sandboxed execution tools, and Coqui library for text-to-speech (TTS) within an agentic orchestration loop. Unlike text-only analysis tools, it adapts responses across modalities and supports multi-turn dialogues grounded in dataset context. In an evaluation of 48 tasks on three datasets, our prototype achieved 95.8% accuracy with model-only generation time under 1.7 seconds (excluding ASR and execution time). A comparison across five LLM sizes (1.5B-32B) revealed accuracy-latency-cost trade-offs, with a 7B model providing the best balance for interactive use. By routing between conversation with user and code execution, constrained to a transparent sandbox, with simultaneously grounding prompts in schema-level context, the Talk2Data agent reliably retrieves actionable insights from tables while making computations verifiable. In the article, except for the Talk2Data agent itself, we discuss implications for human-data interaction, trust in LLM-driven analytics, and future extensions toward large-scale multimodal assistants. △ Less

Submitted 23 November, 2025; originally announced November 2025.

Comments: \c{opyright} 2025 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses

Iris: First-Class Multi-GPU Programming Experience in Triton

Authors: Muhammad Awad, Muhammad Osama, Brandon Potter

Abstract: Multi-GPU programming traditionally requires developers to navigate complex trade-offs between performance and programmability. High-performance implementations typically rely on low-level HIP/CUDA communication libraries that demand substantial engineering effort for even basic overlap patterns, while simpler abstractions often sacrifice performance. We present Iris, a multi-GPU communication lib… ▽ More Multi-GPU programming traditionally requires developers to navigate complex trade-offs between performance and programmability. High-performance implementations typically rely on low-level HIP/CUDA communication libraries that demand substantial engineering effort for even basic overlap patterns, while simpler abstractions often sacrifice performance. We present Iris, a multi-GPU communication library implemented entirely in Python and Triton that eliminates this trade-off. Iris provides tile-based symmetric memory abstractions that naturally align with Triton's programming model, enabling developers to write single-source kernels that seamlessly interleave computation and communication. We demonstrate a taxonomy of compute-communication overlap patterns--from bulk-synchronous to fine-grained workgroup specialization--that can be implemented with minimal code changes in Iris, often requiring just a few additional lines within the same Triton kernel. Our evaluation shows that Iris achieves near-optimal bandwidth utilization in microbenchmarks and delivers up to 1.79x speedup over PyTorch and RCCL for GEMM+All-Scatter workloads, demonstrating that high-level implementations can match or exceed heavily-optimized libraries while dramatically simplifying multi-GPU programming. △ Less

Submitted 16 November, 2025; originally announced November 2025.

Eliminating Multi-GPU Performance Taxes: A Systems Approach to Efficient Distributed LLMs

Authors: Octavian Alexandru Trifan, Karthik Sangaiah, Muhammad Awad, Muhammad Osama, Sumanth Gudaparthi, Alexandru Nicolau, Alexander Veidenbaum, Ganesh Dasika

Abstract: As large language models (LLMs) continue to scale, their workloads increasingly rely on distributed execution across multiple GPUs. However, the conventional bulk synchronous parallel~(BSP) model used in such settings introduces significant performance inefficiencies. To characterize these bottlenecks, we introduce the ''Three Taxes'' (Bulk Synchronous, Inter-Kernel Data Locality, and Kernel Launc… ▽ More As large language models (LLMs) continue to scale, their workloads increasingly rely on distributed execution across multiple GPUs. However, the conventional bulk synchronous parallel~(BSP) model used in such settings introduces significant performance inefficiencies. To characterize these bottlenecks, we introduce the ''Three Taxes'' (Bulk Synchronous, Inter-Kernel Data Locality, and Kernel Launch Overhead) as an analytical framework. We propose moving beyond the rigid BSP model to address key inefficiencies in distributed GPU execution. By exploiting libraries like Iris for Triton, we gain access to in-kernel communication primitives that enable the design of novel fine-grained programming patterns, offering greater flexibility and performance than traditional BSP-based approaches. These patterns systematically eliminate the three taxes by creating direct, tile-level producer-consumer pipelines and replacing global barriers with fine-grained dataflow synchronization. Applying this methodology to critical kernels, from the foundational All-Gather + general matrix multiplication operation to the complex Flash Decode algorithm, we observe a 10-20% speedup in end-to-end latency over BSP-based approaches, establishing a more programmable and efficient paradigm for distributed LLM workloads. △ Less

Submitted 3 November, 2025; originally announced November 2025.

SwizzlePerf: Hardware-Aware LLMs for GPU Kernel Performance Optimization

Authors: Arya Tschand, Muhammad Awad, Ryan Swann, Kesavan Ramakrishnan, Jeffrey Ma, Keith Lowery, Ganesh Dasika, Vijay Janapa Reddi

Abstract: Large language models (LLMs) have shown progress in GPU kernel performance engineering using inefficient search-based methods that optimize around runtime. Any existing approach lacks a key characteristic that human performance engineers rely on for near-optimal utilization -- hardware-awareness. By leveraging the workload's specific memory access patterns, architecture specifications, filtered pr… ▽ More Large language models (LLMs) have shown progress in GPU kernel performance engineering using inefficient search-based methods that optimize around runtime. Any existing approach lacks a key characteristic that human performance engineers rely on for near-optimal utilization -- hardware-awareness. By leveraging the workload's specific memory access patterns, architecture specifications, filtered profiling logs, and reflections on historical performance, we can make software-level optimizations that are tailored to the underlying hardware. SwizzlePerf automatically generates spatial optimizations for GPU kernels on disaggregated architectures by giving LLMs explicit hardware-awareness. For a GEMM kernel, SwizzlePerf takes less than 5 minutes to generate the same hardware-specific optimal swizzling pattern that took expert performance engineers 2 weeks to find. On a suite of 10 diverse ML and Science kernels, SwizzlePerf can generate swizzling patterns for 9 of the kernels that achieve up to a 2.06x speedup and 70% improvement in L2 hit rate. This work is the first of many steps toward systematically creating hardware-aware LLM performance engineering agents. △ Less

Submitted 27 August, 2025; originally announced August 2025.

Can Small-Scale Data Poisoning Exacerbate Dialect-Linked Biases in Large Language Models?

Authors: Chaymaa Abbas, Mariette Awad, Razane Tajeddine

Abstract: Style-conditioned data poisoning is identified as a covert vector for amplifying sociolinguistic bias in large language models. Using small poisoned budgets that pair dialectal prompts -- principally African American Vernacular English (AAVE) and a Southern dialect -- with toxic or stereotyped completions during instruction tuning, this work probes whether linguistic style can act as a latent trig… ▽ More Style-conditioned data poisoning is identified as a covert vector for amplifying sociolinguistic bias in large language models. Using small poisoned budgets that pair dialectal prompts -- principally African American Vernacular English (AAVE) and a Southern dialect -- with toxic or stereotyped completions during instruction tuning, this work probes whether linguistic style can act as a latent trigger for harmful behavior. Across multiple model families and scales, poisoned exposure elevates toxicity and stereotype expression for dialectal inputs -- most consistently for AAVE -- while Standard American English remains comparatively lower yet not immune. A multi-metric audit combining classifier-based toxicity with an LLM-as-a-judge reveals stereotype-laden content even when lexical toxicity appears muted, indicating that conventional detectors under-estimate sociolinguistic harms. Additionally, poisoned models exhibit emergent jailbreaking despite the absence of explicit slurs in the poison, suggesting weakened alignment rather than memorization. These findings underscore the need for dialect-aware evaluation, content-level stereotype auditing, and training protocols that explicitly decouple style from toxicity to prevent bias amplification through seemingly minor, style-based contamination. △ Less

Submitted 9 October, 2025; v1 submitted 25 July, 2025; originally announced July 2025.

Omniwise: Predicting GPU Kernels Performance with LLMs

Authors: Zixian Wang, Cole Ramos, Muhammad A. Awad, Keith Lowery

Abstract: In recent years, the rapid advancement of deep neural networks (DNNs) has revolutionized artificial intelligence, enabling models with unprecedented capabilities in understanding, generating, and processing complex data. These powerful architectures have transformed a wide range of downstream applications, tackling tasks beyond human reach. In this paper, we introduce Omniwise, the first end-to-en… ▽ More In recent years, the rapid advancement of deep neural networks (DNNs) has revolutionized artificial intelligence, enabling models with unprecedented capabilities in understanding, generating, and processing complex data. These powerful architectures have transformed a wide range of downstream applications, tackling tasks beyond human reach. In this paper, we introduce Omniwise, the first end-to-end, self-supervised fine-tuning pipeline that applies large language models (LLMs) to GPU kernel performance prediction--a novel use case in performance profiling. Omniwise is model-agnostic and lightweight, achieving strong results even with a small 3B-parameter model. It can predict key performance metrics, including memory bandwidth, cache hit rates, GFLOPs, and arithmetic intensity, directly from kernel code without the need for code execution or profiling tools. Our approach achieves over 90% of predictions within 10% relative error on GPU kernels executed on AMD MI250 and MI300X architectures. In addition to the pipeline, we develop an online inference server and a Visual Studio Code plugin that seamlessly integrate LLM-based performance prediction into developers' workflows. △ Less

Submitted 25 June, 2025; originally announced June 2025.

ECHO-LLaMA: Efficient Caching for High-Performance LLaMA Training

Authors: Maryam Dialameh, Rezaul Karim, Hossein Rajabzadeh, Omar Mohamed Awad, Hyock Ju Kwon, Boxing Chen, Walid Ahmed, Yang Liu

Abstract: This paper introduces ECHO-LLaMA, an efficient LLaMA architecture designed to improve both the training speed and inference throughput of LLaMA architectures while maintaining its learning capacity. ECHO-LLaMA transforms LLaMA models into shared KV caching across certain layers, significantly reducing KV computational complexity while maintaining or improving language performance. Experimental res… ▽ More This paper introduces ECHO-LLaMA, an efficient LLaMA architecture designed to improve both the training speed and inference throughput of LLaMA architectures while maintaining its learning capacity. ECHO-LLaMA transforms LLaMA models into shared KV caching across certain layers, significantly reducing KV computational complexity while maintaining or improving language performance. Experimental results demonstrate that ECHO-LLaMA achieves up to 77\% higher token-per-second throughput during training, up to 16\% higher Model FLOPs Utilization (MFU), and up to 14\% lower loss when trained on an equal number of tokens. Furthermore, on the 1.1B model, ECHO-LLaMA delivers approximately 7\% higher test-time throughput compared to the baseline. By introducing a computationally efficient adaptation mechanism, ECHO-LLaMA offers a scalable and cost-effective solution for pretraining and finetuning large language models, enabling faster and more resource-efficient training without compromising performance. △ Less

Submitted 21 June, 2025; v1 submitted 22 May, 2025; originally announced May 2025.

AraSTEM: A Native Arabic Multiple Choice Question Benchmark for Evaluating LLMs Knowledge In STEM Subjects

Authors: Ahmad Mustapha, Hadi Al-Khansa, Hadi Al-Mubasher, Aya Mourad, Ranam Hamoud, Hasan El-Husseini, Marwah Al-Sakkaf, Mariette Awad

Abstract: Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks and asses the various aspects of LLMs including knowledge and reasoning. Numerous benchmarks have been developed to evaluate LLMs knowledge, but they predominantl… ▽ More Large Language Models (LLMs) have shown remarkable capabilities, not only in generating human-like text, but also in acquiring knowledge. This highlights the need to go beyond the typical Natural Language Processing downstream benchmarks and asses the various aspects of LLMs including knowledge and reasoning. Numerous benchmarks have been developed to evaluate LLMs knowledge, but they predominantly focus on the English language. Given that many LLMs are multilingual, relying solely on benchmarking English knowledge is insufficient. To address this issue, we introduce AraSTEM, a new Arabic multiple-choice question dataset aimed at evaluating LLMs knowledge in STEM subjects. The dataset spans a range of topics at different levels which requires models to demonstrate a deep understanding of scientific Arabic in order to achieve high accuracy. Our findings show that publicly available models of varying sizes struggle with this dataset, and underscores the need for more localized language models. The dataset is freely accessible on Hugging Face. △ Less

Submitted 31 December, 2024; originally announced January 2025.

An Unsupervised Anomaly Detection in Electricity Consumption Using Reinforcement Learning and Time Series Forest Based Framework

Authors: Jihan Ghanim, Mariette Awad

Abstract: Anomaly detection (AD) plays a crucial role in time series applications, primarily because time series data is employed across real-world scenarios. Detecting anomalies poses significant challenges since anomalies take diverse forms making them hard to pinpoint accurately. Previous research has explored different AD models, making specific assumptions with varying sensitivity toward particular ano… ▽ More Anomaly detection (AD) plays a crucial role in time series applications, primarily because time series data is employed across real-world scenarios. Detecting anomalies poses significant challenges since anomalies take diverse forms making them hard to pinpoint accurately. Previous research has explored different AD models, making specific assumptions with varying sensitivity toward particular anomaly types. To address this issue, we propose a novel model selection for unsupervised AD using a combination of time series forest (TSF) and reinforcement learning (RL) approaches that dynamically chooses an AD technique. Our approach allows for effective AD without explicitly depending on ground truth labels that are often scarce and expensive to obtain. Results from the real-time series dataset demonstrate that the proposed model selection approach outperforms all other AD models in terms of the F1 score metric. For the synthetic dataset, our proposed model surpasses all other AD models except for KNN, with an impressive F1 score of 0.989. The proposed model selection framework also exceeded the performance of GPT-4 when prompted to act as an anomaly detector on the synthetic dataset. Exploring different reward functions revealed that the original reward function in our proposed AD model selection approach yielded the best overall scores. We evaluated the performance of the six AD models on an additional three datasets, having global, local, and clustered anomalies respectively, showing that each AD model exhibited distinct performance depending on the type of anomalies. This emphasizes the significance of our proposed AD model selection framework, maintaining high performance across all datasets, and showcasing superior performance across different anomaly types. △ Less

Submitted 30 December, 2024; originally announced January 2025.

Context-Based Meta Reinforcement Learning for Robust and Adaptable Peg-in-Hole Assembly Tasks

Authors: Ahmed Shokry, Walid Gomaa, Tobias Zaenker, Murad Dawood, Rohit Menon, Shady A. Maged, Mohammed I. Awad, Maren Bennewitz

Abstract: Autonomous assembly is an essential capability for industrial and service robots, with Peg-in-Hole (PiH) insertion being one of the core tasks. However, PiH assembly in unknown environments is still challenging due to uncertainty in task parameters, such as the hole position and orientation, resulting from sensor noise. Although context-based meta reinforcement learning (RL) methods have been prev… ▽ More Autonomous assembly is an essential capability for industrial and service robots, with Peg-in-Hole (PiH) insertion being one of the core tasks. However, PiH assembly in unknown environments is still challenging due to uncertainty in task parameters, such as the hole position and orientation, resulting from sensor noise. Although context-based meta reinforcement learning (RL) methods have been previously presented to adapt to unknown task parameters in PiH assembly tasks, the performance depends on a sample-inefficient procedure or human demonstrations. Thus, to enhance the applicability of meta RL in real-world PiH assembly tasks, we propose to train the agent to use information from the robot's forward kinematics and an uncalibrated camera. Furthermore, we improve the performance by efficiently adapting the meta-trained agent to use data from force/torque sensor. Finally, we propose an adaptation procedure for out-of-distribution tasks whose parameters are different from the training tasks. Experiments on simulated and real robots prove that our modifications enhance the sample efficiency during meta training, real-world adaptation performance, and generalization of the context-based meta RL agent in PiH assembly tasks compared to previous approaches. △ Less

Submitted 18 October, 2025; v1 submitted 24 September, 2024; originally announced September 2024.

Eye Tracking on Text Reading with Visual Enhancements

Authors: Franziska Huth, Maurice Koch, Miriam Awad, Daniel Weiskopf, Kuno Kurzhals

Abstract: The interplay between text and visualization is gaining importance for media where traditional text is enriched by visual elements to improve readability and emphasize facts. In two controlled eye-tracking experiments ($N=12$), we approach answers to the question: How do visualization techniques influence reading behavior? We compare plain text to that marked with highlights, icons, and word-sized… ▽ More The interplay between text and visualization is gaining importance for media where traditional text is enriched by visual elements to improve readability and emphasize facts. In two controlled eye-tracking experiments ($N=12$), we approach answers to the question: How do visualization techniques influence reading behavior? We compare plain text to that marked with highlights, icons, and word-sized data visualizations. We assess quantitative metrics~(eye movement, completion time, error rate) and subjective feedback~(personal preference and ratings). The results indicate that visualization techniques, especially in the first experiment, show promising trends for improved reading behavior. The results also show the need for further research to make reading more effective and inform suggestions for future studies. △ Less

Submitted 8 April, 2024; originally announced April 2024.

A Novel Bioinspired Neuromorphic Vision-based Tactile Sensor for Fast Tactile Perception

Authors: Omar Faris, Mohammad I. Awad, Murana A. Awad, Yahya Zweiri, Kinda Khalaf

Abstract: Tactile sensing represents a crucial technique that can enhance the performance of robotic manipulators in various tasks. This work presents a novel bioinspired neuromorphic vision-based tactile sensor that uses an event-based camera to quickly capture and convey information about the interactions between robotic manipulators and their environment. The camera in the sensor observes the deformation… ▽ More Tactile sensing represents a crucial technique that can enhance the performance of robotic manipulators in various tasks. This work presents a novel bioinspired neuromorphic vision-based tactile sensor that uses an event-based camera to quickly capture and convey information about the interactions between robotic manipulators and their environment. The camera in the sensor observes the deformation of a flexible skin manufactured from a cheap and accessible 3D printed material, whereas a 3D printed rigid casing houses the components of the sensor together. The sensor is tested in a grasping stage classification task involving several objects using a data-driven learning-based approach. The results show that the proposed approach enables the sensor to detect pressing and slip incidents within a speed of 2 ms. The fast tactile perception properties of the proposed sensor makes it an ideal candidate for safe grasping of different objects in industries that involve high-speed pick-and-place operations. △ Less

Submitted 15 March, 2024; originally announced March 2024.

Comments: 9 pages, 10 figures, journal

SkipViT: Speeding Up Vision Transformers with a Token-Level Skip Connection

Authors: Foozhan Ataiefard, Walid Ahmed, Habib Hajimolahoseini, Saina Asani, Farnoosh Javadi, Mohammad Hassanpour, Omar Mohamed Awad, Austin Wen, Kangling Liu, Yang Liu

Abstract: Vision transformers are known to be more computationally and data-intensive than CNN models. These transformer models such as ViT, require all the input image tokens to learn the relationship among them. However, many of these tokens are not informative and may contain irrelevant information such as unrelated background or unimportant scenery. These tokens are overlooked by the multi-head self-att… ▽ More Vision transformers are known to be more computationally and data-intensive than CNN models. These transformer models such as ViT, require all the input image tokens to learn the relationship among them. However, many of these tokens are not informative and may contain irrelevant information such as unrelated background or unimportant scenery. These tokens are overlooked by the multi-head self-attention (MHSA), resulting in many redundant and unnecessary computations in MHSA and the feed-forward network (FFN). In this work, we propose a method to optimize the amount of unnecessary interactions between unimportant tokens by separating and sending them through a different low-cost computational path. Our method does not add any parameters to the ViT model and aims to find the best trade-off between training throughput and achieving a 0% loss in the Top-1 accuracy of the final model. Our experimental results on training ViT-small from scratch show that SkipViT is capable of effectively dropping 55% of the tokens while gaining more than 13% training throughput and maintaining classification accuracy at the level of the baseline model on Huawei Ascend910A. △ Less

Submitted 26 January, 2024; originally announced January 2024.

On The Potential of The Fractal Geometry and The CNNs Ability to Encode it

Authors: Julia El Zini, Bassel Musharrafieh, Mariette Awad

Abstract: The fractal dimension provides a statistical index of object complexity by studying how the pattern changes with the measuring scale. Although useful in several classification tasks, the fractal dimension is under-explored in deep learning applications. In this work, we investigate the features that are learned by deep models and we study whether these deep networks are able to encode features as… ▽ More The fractal dimension provides a statistical index of object complexity by studying how the pattern changes with the measuring scale. Although useful in several classification tasks, the fractal dimension is under-explored in deep learning applications. In this work, we investigate the features that are learned by deep models and we study whether these deep networks are able to encode features as complex and high-level as the fractal dimensions. Specifically, we conduct a correlation analysis experiment to show that deep networks are not able to extract such a feature in none of their layers. We combine our analytical study with a human evaluation to investigate the differences between deep learning networks and models that operate on the fractal feature solely. Moreover, we show the effectiveness of fractal features in applications where the object structure is crucial for the classification task. We empirically show that training a shallow network on fractal features achieves performance comparable, even superior in specific cases, to that of deep networks trained on raw data while requiring less computational resources. Fractals improved the accuracy of the classification by 30% on average while requiring up to 84% less time to train. We couple our empirical study with a complexity analysis of the computational cost of extracting the proposed fractal features, and we study its limitation. △ Less

Submitted 7 January, 2024; originally announced January 2024.

SwiftLearn: A Data-Efficient Training Method of Deep Learning Models using Importance Sampling

Authors: Habib Hajimolahoseini, Omar Mohamed Awad, Walid Ahmed, Austin Wen, Saina Asani, Mohammad Hassanpour, Farnoosh Javadi, Mehdi Ahmadi, Foozhan Ataiefard, Kangling Liu, Yang Liu

Abstract: In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of training. This subset is selected based on an importance criteria measured over the entire dataset during warm-up stages, aiming to preserve the model performance with fewer examples during the rest of training. The impo… ▽ More In this paper, we present SwiftLearn, a data-efficient approach to accelerate training of deep learning models using a subset of data samples selected during the warm-up stages of training. This subset is selected based on an importance criteria measured over the entire dataset during warm-up stages, aiming to preserve the model performance with fewer examples during the rest of training. The importance measure we propose could be updated during training every once in a while, to make sure that all of the data samples have a chance to return to the training loop if they show a higher importance. The model architecture is unchanged but since the number of data samples controls the number of forward and backward passes during training, we can reduce the training time by reducing the number of training samples used in each epoch of training. Experimental results on a variety of CV and NLP models during both pretraining and finetuning show that the model performance could be preserved while achieving a significant speed-up during training. More specifically, BERT finetuning on GLUE benchmark shows that almost 90% of the data can be dropped achieving an end-to-end average speedup of 3.36x while keeping the average accuracy drop less than 0.92%. △ Less

Submitted 25 November, 2023; originally announced November 2023.

GQKVA: Efficient Pre-training of Transformers by Grouping Queries, Keys, and Values

Authors: Farnoosh Javadi, Walid Ahmed, Habib Hajimolahoseini, Foozhan Ataiefard, Mohammad Hassanpour, Saina Asani, Austin Wen, Omar Mohamed Awad, Kangling Liu, Yang Liu

Abstract: Massive transformer-based models face several challenges, including slow and computationally intensive pre-training and over-parametrization. This paper addresses these challenges by proposing a versatile method called GQKVA, which generalizes query, key, and value grouping techniques. GQKVA is designed to speed up transformer pre-training while reducing the model size. Our experiments with variou… ▽ More Massive transformer-based models face several challenges, including slow and computationally intensive pre-training and over-parametrization. This paper addresses these challenges by proposing a versatile method called GQKVA, which generalizes query, key, and value grouping techniques. GQKVA is designed to speed up transformer pre-training while reducing the model size. Our experiments with various GQKVA variants highlight a clear trade-off between performance and model size, allowing for customized choices based on resource and time limitations. Our findings also indicate that the conventional multi-head attention approach is not always the best choice, as there are lighter and faster alternatives available. We tested our method on ViT, which achieved an approximate 0.3% increase in accuracy while reducing the model size by about 4% in the task of image classification. Additionally, our most aggressive model reduction experiment resulted in a reduction of approximately 15% in model size, with only around a 1% drop in accuracy. △ Less

Submitted 13 December, 2023; v1 submitted 6 November, 2023; originally announced November 2023.

Improving Resnet-9 Generalization Trained on Small Datasets

Authors: Omar Mohamed Awad, Habib Hajimolahoseini, Michael Lim, Gurpreet Gosal, Walid Ahmed, Yang Liu, Gordon Deng

Abstract: This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training. The challenge is to achieve the highest possible accuracy in an image classification task in less than 10 minutes. The training is done on a small dataset of 5000 images picked randomly from CIFAR-10 dataset. The evaluation is performed by the competition organizers on a… ▽ More This paper presents our proposed approach that won the first prize at the ICLR competition on Hardware Aware Efficient Training. The challenge is to achieve the highest possible accuracy in an image classification task in less than 10 minutes. The training is done on a small dataset of 5000 images picked randomly from CIFAR-10 dataset. The evaluation is performed by the competition organizers on a secret dataset with 1000 images of the same size. Our approach includes applying a series of technique for improving the generalization of ResNet-9 including: sharpness aware optimization, label smoothing, gradient centralization, input patch whitening as well as metalearning based training. Our experiments show that the ResNet-9 can achieve the accuracy of 88% while trained only on a 10% subset of CIFAR-10 dataset in less than 10 minuets △ Less

Submitted 7 September, 2023; originally announced September 2023.

BOBA: A Parallel Lightweight Graph Reordering Algorithm with Heavyweight Implications

Authors: Matthew Drescher, Muhammad A. Awad, Serban D. Porumbescu, John D. Owens

Abstract: We describe a simple parallel-friendly lightweight graph reordering algorithm for COO graphs (edge lists). Our ``Batched Order By Attachment'' (BOBA) algorithm is linear in the number of edges in terms of reads and linear in the number of vertices for writes through to main memory. It is highly parallelizable on GPUs\@. We show that, compared to a randomized baseline, the ordering produced gives… ▽ More We describe a simple parallel-friendly lightweight graph reordering algorithm for COO graphs (edge lists). Our ``Batched Order By Attachment'' (BOBA) algorithm is linear in the number of edges in terms of reads and linear in the number of vertices for writes through to main memory. It is highly parallelizable on GPUs\@. We show that, compared to a randomized baseline, the ordering produced gives improved locality of reference in sparse matrix-vector multiplication (SpMV) as well as other graph algorithms. Moreover, it can substantially speed up the conversion from a COO representation to the compressed format CSR, a very common workflow. Thus, it can give \emph{end-to-end} speedups even in SpMV\@. Unlike other lightweight approaches, this reordering does not rely on explicitly knowing the degrees of the vertices, and indeed its runtime is comparable to that of computing degrees. Instead, it uses the structure and edge distribution inherent in the input edge list, making it a candidate for default use in a pragmatic graph creation pipeline. This algorithm is suitable for road-type networks as well as scale-free. It improves cache locality on both CPUs and GPUs, achieving hit rates similar to the heavyweight techniques (e.g., for SpMV, 7--52\% and 11--67\% in the L1 and L2 caches, respectively). Compared to randomly labeled graphs, BOBA-reordered graphs achieve end-to-end speedups of up to 3.45. The reordering time is approximately one order of magnitude faster than existing lightweight techniques and up to 2.5 orders of magnitude faster than heavyweight techniques. △ Less

Submitted 21 June, 2023; v1 submitted 17 June, 2023; originally announced June 2023.

FedCSD: A Federated Learning Based Approach for Code-Smell Detection

Authors: Sadi Alawadi, Khalid Alkharabsheh, Fahed Alkhabbas, Victor Kebande, Feras M. Awaysheh, Fabio Palomba, Mohammed Awad

Abstract: This paper proposes a Federated Learning Code Smell Detection (FedCSD) approach that allows organizations to collaboratively train federated ML models while preserving their data privacy. These assertions have been supported by three experiments that have significantly leveraged three manually validated datasets aimed at detecting and examining different code smell scenarios. In experiment 1, whic… ▽ More This paper proposes a Federated Learning Code Smell Detection (FedCSD) approach that allows organizations to collaboratively train federated ML models while preserving their data privacy. These assertions have been supported by three experiments that have significantly leveraged three manually validated datasets aimed at detecting and examining different code smell scenarios. In experiment 1, which was concerned with a centralized training experiment, dataset two achieved the lowest accuracy (92.30%) with fewer smells, while datasets one and three achieved the highest accuracy with a slight difference (98.90% and 99.5%, respectively). This was followed by experiment 2, which was concerned with cross-evaluation, where each ML model was trained using one dataset, which was then evaluated over the other two datasets. Results from this experiment show a significant drop in the model's accuracy (lowest accuracy: 63.80\%) where fewer smells exist in the training dataset, which has a noticeable reflection (technical debt) on the model's performance. Finally, the last and third experiments evaluate our approach by splitting the dataset into 10 companies. The ML model was trained on the company's site, then all model-updated weights were transferred to the server. Ultimately, an accuracy of 98.34% was achieved by the global model that has been trained using 10 companies for 100 training rounds. The results reveal a slight difference in the global model's accuracy compared to the highest accuracy of the centralized model, which can be ignored in favour of the global model's comprehensive knowledge, lower training cost, preservation of data privacy, and avoidance of the technical debt problem. △ Less

Submitted 26 March, 2024; v1 submitted 31 May, 2023; originally announced June 2023.

Comments: 17 pages, 7 figures, Journal paper

Report number: 2169-3536 ACM Class: D.2.4

Journal ref: 25 March 2024

An Asymmetric Loss with Anomaly Detection LSTM Framework for Power Consumption Prediction

Authors: Jihan Ghanim, Maha Issa, Mariette Awad

Abstract: Building an accurate load forecasting model with minimal underpredictions is vital to prevent any undesired power outages due to underproduction of electricity. However, the power consumption patterns of the residential sector contain fluctuations and anomalies making them challenging to predict. In this paper, we propose multiple Long Short-Term Memory (LSTM) frameworks with different asymmetric… ▽ More Building an accurate load forecasting model with minimal underpredictions is vital to prevent any undesired power outages due to underproduction of electricity. However, the power consumption patterns of the residential sector contain fluctuations and anomalies making them challenging to predict. In this paper, we propose multiple Long Short-Term Memory (LSTM) frameworks with different asymmetric loss functions to impose a higher penalty on underpredictions. We also apply a density-based spatial clustering of applications with noise (DBSCAN) anomaly detection approach, prior to the load forecasting task, to remove any present oultiers. Considering the effect of weather and social factors, seasonality splitting is performed on the three considered datasets from France, Germany, and Hungary containing hourly power consumption, weather, and calendar features. Root-mean-square error (RMSE) results show that removing the anomalies efficiently reduces the underestimation and overestimation errors in all the seasonal datasets. Additionally, asymmetric loss functions and seasonality splitting effectively minimize underestimations despite increasing the overestimation error to some degree. Reducing underpredictions of electricity consumption is essential to prevent power outages that can be damaging to the community. △ Less

Submitted 5 February, 2023; originally announced February 2023.

Comments: This paper was published in 2022 IEEE 21st Mediterranean Electrotechnical Conference (MELECON)

Spatio-Temporal Graph Neural Networks: A Survey

Authors: Zahraa Al Sahili, Mariette Awad

Abstract: Graph Neural Networks have gained huge interest in the past few years. These powerful algorithms expanded deep learning models to non-Euclidean space and were able to achieve state of art performance in various applications including recommender systems and social networks. However, this performance is based on static graph structures assumption which limits the Graph Neural Networks performance w… ▽ More Graph Neural Networks have gained huge interest in the past few years. These powerful algorithms expanded deep learning models to non-Euclidean space and were able to achieve state of art performance in various applications including recommender systems and social networks. However, this performance is based on static graph structures assumption which limits the Graph Neural Networks performance when the data varies with time. Spatiotemporal Graph Neural Networks are extension of Graph Neural Networks that takes the time factor into account. Recently, various Spatiotemporal Graph Neural Network algorithms were proposed and achieved superior performance compared to other deep learning algorithms in several time dependent applications. This survey discusses interesting topics related to Spatiotemporal Graph Neural Networks, including algorithms, applications, and open challenges. △ Less

Submitted 11 February, 2023; v1 submitted 25 January, 2023; originally announced January 2023.

CEnt: An Entropy-based Model-agnostic Explainability Framework to Contrast Classifiers' Decisions

Authors: Julia El Zini, Mohammad Mansour, Mariette Awad

Abstract: Current interpretability methods focus on explaining a particular model's decision through present input features. Such methods do not inform the user of the sufficient conditions that alter these decisions when they are not desirable. Contrastive explanations circumvent this problem by providing explanations of the form "If the feature $X>x$, the output $Y$ would be different''. While different a… ▽ More Current interpretability methods focus on explaining a particular model's decision through present input features. Such methods do not inform the user of the sufficient conditions that alter these decisions when they are not desirable. Contrastive explanations circumvent this problem by providing explanations of the form "If the feature $X>x$, the output $Y$ would be different''. While different approaches are developed to find contrasts; these methods do not all deal with mutability and attainability constraints. In this work, we present a novel approach to locally contrast the prediction of any classifier. Our Contrastive Entropy-based explanation method, CEnt, approximates a model locally by a decision tree to compute entropy information of different feature splits. A graph, G, is then built where contrast nodes are found through a one-to-many shortest path search. Contrastive examples are generated from the shortest path to reflect feature splits that alter model decisions while maintaining lower entropy. We perform local sampling on manifold-like distances computed by variational auto-encoders to reflect data density. CEnt is the first non-gradient-based contrastive method generating diverse counterfactuals that do not necessarily exist in the training data while satisfying immutability (ex. race) and semi-immutability (ex. age can only change in an increasing direction). Empirical evaluation on four real-world numerical datasets demonstrates the ability of CEnt in generating counterfactuals that achieve better proximity rates than existing methods without compromising latency, feasibility, and attainability. We further extend CEnt to imagery data to derive visually appealing and useful contrasts between class labels on MNIST and Fashion MNIST datasets. Finally, we show how CEnt can serve as a tool to detect vulnerabilities of textual classifiers. △ Less

Submitted 19 January, 2023; originally announced January 2023.

Beyond Model Interpretability: On the Faithfulness and Adversarial Robustness of Contrastive Textual Explanations

Authors: Julia El Zini, Mariette Awad

Abstract: Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impacted by classifiers' decisions. However, their extension to textual data is under-explored and there is little investigation on their vulnerabilities and limitations. This work mot… ▽ More Contrastive explanation methods go beyond transparency and address the contrastive aspect of explanations. Such explanations are emerging as an attractive option to provide actionable change to scenarios adversely impacted by classifiers' decisions. However, their extension to textual data is under-explored and there is little investigation on their vulnerabilities and limitations. This work motivates textual counterfactuals by laying the ground for a novel evaluation scheme inspired by the faithfulness of explanations. Accordingly, we extend the computation of three metrics, proximity,connectedness and stability, to textual data and we benchmark two successful contrastive methods, POLYJUICE and MiCE, on our suggested metrics. Experiments on sentiment analysis data show that the connectedness of counterfactuals to their original counterparts is not obvious in both models. More interestingly, the generated contrastive texts are more attainable with POLYJUICE which highlights the significance of latent representations in counterfactual search. Finally, we perform the first semantic adversarial attack on textual recourse methods. The results demonstrate the robustness of POLYJUICE and the role that latent input representations play in robustness and reliability. △ Less

Submitted 17 October, 2022; originally announced October 2022.

On the Explainability of Natural Language Processing Deep Models

Authors: Julia El Zini, Mariette Awad

Abstract: While there has been a recent explosion of work on ExplainableAI ExAI on deep models that operate on imagery and tabular data, textual datasets present new challenges to the ExAI community. Such challenges can be attributed to the lack of input structure in textual data, the use of word embeddings that add to the opacity of the models and the difficulty of the visualization of the inner workings o… ▽ More While there has been a recent explosion of work on ExplainableAI ExAI on deep models that operate on imagery and tabular data, textual datasets present new challenges to the ExAI community. Such challenges can be attributed to the lack of input structure in textual data, the use of word embeddings that add to the opacity of the models and the difficulty of the visualization of the inner workings of deep models when they are trained on textual data. Lately, methods have been developed to address the aforementioned challenges and present satisfactory explanations on Natural Language Processing (NLP) models. However, such methods are yet to be studied in a comprehensive framework where common challenges are properly stated and rigorous evaluation practices and metrics are proposed. Motivated to democratize ExAI methods in the NLP field, we present in this work a survey that studies model-agnostic as well as model-specific explainability methods on NLP models. Such methods can either develop inherently interpretable NLP models or operate on pre-trained models in a post-hoc manner. We make this distinction and we further decompose the methods into three categories according to what they explain: (1) word embeddings (input-level), (2) inner workings of NLP models (processing-level) and (3) models' decisions (output-level). We also detail the different evaluation approaches interpretability methods in the NLP field. Finally, we present a case-study on the well-known neural machine translation in an appendix and we propose promising future research directions for ExAI in the NLP field. △ Less

Submitted 13 October, 2022; originally announced October 2022.

Journal ref: ACM Computing Surveys, March 2022

On the Evaluation of the Plausibility and Faithfulness of Sentiment Analysis Explanations

Authors: Julia El Zini, Mohamad Mansour, Basel Mousi, Mariette Awad

Abstract: Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption. In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the ex… ▽ More Current Explainable AI (ExAI) methods, especially in the NLP field, are conducted on various datasets by employing different metrics to evaluate several aspects. The lack of a common evaluation framework is hindering the progress tracking of such methods and their wider adoption. In this work, inspired by offline information retrieval, we propose different metrics and techniques to evaluate the explainability of SA models from two angles. First, we evaluate the strength of the extracted "rationales" in faithfully explaining the predicted outcome. Second, we measure the agreement between ExAI methods and human judgment on a homegrown dataset1 to reflect on the rationales plausibility. Our conducted experiments comprise four dimensions: (1) the underlying architectures of SA models, (2) the approach followed by the ExAI method, (3) the reasoning difficulty, and (4) the homogeneity of the ground-truth rationales. We empirically demonstrate that anchors explanations are more aligned with the human judgment and can be more confident in extracting supporting rationales. As can be foreseen, the reasoning complexity of sentiment is shown to thwart ExAI methods from extracting supporting evidence. Moreover, a remarkable discrepancy is discerned between the results of different explainability methods on the various architectures suggesting the need for consolidation to observe enhanced performance. Predominantly, transformers are shown to exhibit better explainability than convolutional and recurrent architectures. Our work paves the way towards designing more interpretable NLP models and enabling a common evaluation ground for their relative strengths and robustness. △ Less

Submitted 13 October, 2022; originally announced October 2022.

Comments: 13 pages, 3 figures, conference (AIAI - springer)

Journal ref: Artificial Intelligence Applications and Innovations. AIAI 2022. IFIP Advances in Information and Communication Technology, vol 647. Springer, Cham

Novel Supernumerary Robotic Limb based on Variable Stiffness Actuators for Hemiplegic Patients Assistance

Authors: Basma B. Hasanen, Mohammad I. Awad, Mohamed N. Boushaki, Zhenwei Niu, Mohammed A. Ramadan, Irfan Hussain

Abstract: Loss of upper extremity motor control and function is an unremitting symptom in post-stroke patients. This would impose hardships on accomplishing their daily life activities. Supernumerary robotic limbs (SRLs) were introduced as a solution to regain the lost Degrees of Freedom (DoFs) by introducing an independent new limb. The actuation systems in SRL can be categorized into rigid and soft actuat… ▽ More Loss of upper extremity motor control and function is an unremitting symptom in post-stroke patients. This would impose hardships on accomplishing their daily life activities. Supernumerary robotic limbs (SRLs) were introduced as a solution to regain the lost Degrees of Freedom (DoFs) by introducing an independent new limb. The actuation systems in SRL can be categorized into rigid and soft actuators. Soft actuators have proven advantageous over their rigid counterparts through intrinsic safety, cost, and energy efficiency. However, they suffer from low stiffness, which jeopardizes their accuracy. Variable Stiffness Actuators (VSAs) are newly developed technologies that have been proven to ensure accuracy and safety. In this paper, we introduce the novel Supernumerary Robotic Limb based on Variable Stiffness Actuators. Based on our knowledge, the proposed proof-of-concept SRL is the first that utilizes Variable Stiffness Actuators. The developed SRL would assist post-stroke patients in bi-manual tasks, e.g., eating with a fork and knife. The modeling, design, and realization of the system are illustrated. The proposed SRL was evaluated and verified for its accuracy via predefined trajectories. The safety was verified by utilizing the momentum observer for collision detection, and several post-collision reaction strategies were evaluated through the Soft Tissue Injury Test. The assistance process is qualitatively verified through standard user-satisfaction questionnaire. △ Less

Submitted 6 August, 2022; originally announced August 2022.

Comments: 8 pages, 11 figures, Proceedings of the 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022)

The Power of Transfer Learning in Agricultural Applications: AgriNet

Authors: Zahraa Al Sahili, Mariette Awad

Abstract: Advances in deep learning and transfer learning have paved the way for various automation classification tasks in agriculture, including plant diseases, pests, weeds, and plant species detection. However, agriculture automation still faces various challenges, such as the limited size of datasets and the absence of plant-domain-specific pretrained models. Domain specific pretrained models have show… ▽ More Advances in deep learning and transfer learning have paved the way for various automation classification tasks in agriculture, including plant diseases, pests, weeds, and plant species detection. However, agriculture automation still faces various challenges, such as the limited size of datasets and the absence of plant-domain-specific pretrained models. Domain specific pretrained models have shown state of art performance in various computer vision tasks including face recognition and medical imaging diagnosis. In this paper, we propose AgriNet dataset, a collection of 160k agricultural images from more than 19 geographical locations, several images captioning devices, and more than 423 classes of plant species and diseases. We also introduce AgriNet models, a set of pretrained models on five ImageNet architectures: VGG16, VGG19, Inception-v3, InceptionResNet-v2, and Xception. AgriNet-VGG19 achieved the highest classification accuracy of 94 % and the highest F1-score of 92%. Additionally, all proposed models were found to accurately classify the 423 classes of plant species, diseases, pests, and weeds with a minimum accuracy of 87% for the Inception-v3 model.Finally, experiments to evaluate of superiority of AgriNet models compared to ImageNet models were conducted on two external datasets: pest and plant diseases dataset from Bangladesh and a plant diseases dataset from Kashmir. △ Less

Submitted 6 October, 2022; v1 submitted 8 July, 2022; originally announced July 2022.

Comments: Accepted by Frontiers in Plant Science

Drift Reduction for Monocular Visual Odometry of Intelligent Vehicles using Feedforward Neural Networks

Authors: Hassan Wagih, Mostafa Osman, Mohamed I. Awad, Sherif Hammad

Abstract: In this paper, an approach for reducing the drift in monocular visual odometry algorithms is proposed based on a feedforward neural network. A visual odometry algorithm computes the incremental motion of the vehicle between the successive camera frames, then integrates these increments to determine the pose of the vehicle. The proposed neural network reduces the errors in the pose estimation of th… ▽ More In this paper, an approach for reducing the drift in monocular visual odometry algorithms is proposed based on a feedforward neural network. A visual odometry algorithm computes the incremental motion of the vehicle between the successive camera frames, then integrates these increments to determine the pose of the vehicle. The proposed neural network reduces the errors in the pose estimation of the vehicle which results from the inaccuracies in features detection and matching, camera intrinsic parameters, and so on. These inaccuracies are propagated to the motion estimation of the vehicle causing larger amounts of estimation errors. The drift reducing neural network identifies such errors based on the motion of features in the successive camera frames leading to more accurate incremental motion estimates. The proposed drift reducing neural network is trained and validated using the KITTI dataset and the results show the efficacy of the proposed approach in reducing the errors in the incremental orientation estimation, thus reducing the overall error in the pose estimation. △ Less

Submitted 2 July, 2022; originally announced July 2022.

Comments: This paper contains 6 pages and 10 figures. The paper was accepted for publication in the 25th IEEE International Conference on Intelligent Transportation Systems (IEEE ITSC 2022)

Towards Cross-Disaster Building Damage Assessment with Graph Convolutional Networks

Authors: Ali Ismail, Mariette Awad

Abstract: In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations. Current convolutional neural network approaches do not consider the similarities between neighboring buildings for predicting the damage. We present a novel graph-based building damage detection solution to capture these relationships. Our proposed model architecture learns from both… ▽ More In the aftermath of disasters, building damage maps are obtained using change detection to plan rescue operations. Current convolutional neural network approaches do not consider the similarities between neighboring buildings for predicting the damage. We present a novel graph-based building damage detection solution to capture these relationships. Our proposed model architecture learns from both local and neighborhood features to predict building damage. Specifically, we adopt the sample and aggregate graph convolution strategy to learn aggregation functions that generalize to unseen graphs which is essential for alleviating the time needed to obtain predictions for new disasters. Our experiments on the xBD dataset and comparisons with a classical convolutional neural network reveal that while our approach is handicapped by class imbalance, it presents a promising and distinct advantage when it comes to cross-disaster generalization. △ Less

Submitted 25 January, 2022; originally announced January 2022.

Comments: 5 pages, 3 figures, submitted to IEEE IGARSS 2022

BLDNet: A Semi-supervised Change Detection Building Damage Framework using Graph Convolutional Networks and Urban Domain Knowledge

Authors: Ali Ismail, Mariette Awad

Abstract: Change detection is instrumental to localize damage and understand destruction in disaster informatics. While convolutional neural networks are at the core of recent change detection solutions, we present in this work, BLDNet, a novel graph formulation for building damage change detection and enable learning relationships and representations from both local patterns and non-stationary neighborhood… ▽ More Change detection is instrumental to localize damage and understand destruction in disaster informatics. While convolutional neural networks are at the core of recent change detection solutions, we present in this work, BLDNet, a novel graph formulation for building damage change detection and enable learning relationships and representations from both local patterns and non-stationary neighborhoods. More specifically, we use graph convolutional networks to efficiently learn these features in a semi-supervised framework with few annotated data. Additionally, BLDNet formulation allows for the injection of additional contextual building meta-features. We train and benchmark on the xBD dataset to validate the effectiveness of our approach. We also demonstrate on urban data from the 2020 Beirut Port Explosion that performance is improved by incorporating domain knowledge building meta-features. △ Less

Submitted 25 January, 2022; originally announced January 2022.

Comments: 16 pages, 15 figures, submitted to IEEE Transactions on Geoscience and Remote Sensing

Better GPU Hash Tables

Authors: Muhammad A. Awad, Saman Ashkiani, Serban D. Porumbescu, Martín Farach-Colton, John D. Owens

Abstract: We revisit the problem of building static hash tables on the GPU and design and build three bucketed hash tables that use different probing schemes. Our implementations are lock-free and offer efficient memory access patterns; thus, only the probing scheme is the factor affecting the performance of the hash table's different operations. Our results show that a bucketed cuckoo hash table that uses… ▽ More We revisit the problem of building static hash tables on the GPU and design and build three bucketed hash tables that use different probing schemes. Our implementations are lock-free and offer efficient memory access patterns; thus, only the probing scheme is the factor affecting the performance of the hash table's different operations. Our results show that a bucketed cuckoo hash table that uses three hash functions (BCHT) outperforms alternative methods that use power-of-two choices, iceberg hashing, and a cuckoo hash table that uses a bucket size one. At high load factors as high as 0.99, BCHT enjoys an average probe count of 1.43 during insertion. Using three hash functions only, positive and negative queries require at most 1.39 and 2.8 average probes per key, respectively. △ Less

Submitted 17 December, 2022; v1 submitted 16 August, 2021; originally announced August 2021.

Comments: Our implementation is available at https://github.com/owensgroup/BGHT

Learning to run a Power Network Challenge: a Retrospective Analysis

Authors: Antoine Marot, Benjamin Donnot, Gabriel Dulac-Arnold, Adrian Kelly, Aïdan O'Sullivan, Jan Viebahn, Mariette Awad, Isabelle Guyon, Patrick Panciatici, Camilo Romero

Abstract: Power networks, responsible for transporting electricity across large geographical regions, are complex infrastructures on which modern life critically depend. Variations in demand and production profiles, with increasing renewable energy integration, as well as the high voltage network technology, constitute a real challenge for human operators when optimizing electricity transportation while avo… ▽ More Power networks, responsible for transporting electricity across large geographical regions, are complex infrastructures on which modern life critically depend. Variations in demand and production profiles, with increasing renewable energy integration, as well as the high voltage network technology, constitute a real challenge for human operators when optimizing electricity transportation while avoiding blackouts. Motivated to investigate the potential of AI methods in enabling adaptability in power network operation, we have designed a L2RPN challenge to encourage the development of reinforcement learning solutions to key problems present in the next-generation power networks. The NeurIPS 2020 competition was well received by the international community attracting over 300 participants worldwide. The main contribution of this challenge is our proposed comprehensive 'Grid2Op' framework, and associated benchmark, which plays realistic sequential network operations scenarios. The Grid2Op framework, which is open-source and easily re-usable, allows users to define new environments with its companion GridAlive ecosystem. Grid2Op relies on existing non-linear physical power network simulators and let users create a series of perturbations and challenges that are representative of two important problems: a) the uncertainty resulting from the increased use of unpredictable renewable energy sources, and b) the robustness required with contingent line disconnections. In this paper, we give the competition highlights. We present the benchmark suite and analyse the winning solutions, including one super-human performance demonstration. We propose our organizational insights for a successful competition and conclude on open research avenues. Given the challenge success, we expect our work will foster research to create more sustainable solutions for power network operations. △ Less

Submitted 21 October, 2021; v1 submitted 2 March, 2021; originally announced March 2021.

Journal ref: Proceedings of Machine Learning Research, 2021 NeurIPS 2020 Competition and Demonstration Track

FPRaker: A Processing Element For Accelerating Neural Network Training

Authors: Omar Mohamed Awad, Mostafa Mahmoud, Isak Edo, Ali Hadi Zadeh, Ciaran Bannon, Anand Jayarajan, Gennady Pekhimenko, Andreas Moshovos

Abstract: We present FPRaker, a processing element for composing training accelerators. FPRaker processes several floating-point multiply-accumulation operations concurrently and accumulates their result into a higher precision accumulator. FPRaker boosts performance and energy efficiency during training by taking advantage of the values that naturally appear during training. Specifically, it processes the… ▽ More We present FPRaker, a processing element for composing training accelerators. FPRaker processes several floating-point multiply-accumulation operations concurrently and accumulates their result into a higher precision accumulator. FPRaker boosts performance and energy efficiency during training by taking advantage of the values that naturally appear during training. Specifically, it processes the significand of the operands of each multiply-accumulate as a series of signed powers of two. The conversion to this form is done on-the-fly. This exposes ineffectual work that can be skipped: values when encoded have few terms and some of them can be discarded as they would fall outside the range of the accumulator given the limited precision of floating-point. We demonstrate that FPRaker can be used to compose an accelerator for training and that it can improve performance and energy efficiency compared to using conventional floating-point units under ISO-compute area constraints. We also demonstrate that FPRaker delivers additional benefits when training incorporates pruning and quantization. Finally, we show that FPRaker naturally amplifies performance with training methods that use a different precision per layer. △ Less

Submitted 15 October, 2020; originally announced October 2020.

TensorDash: Exploiting Sparsity to Accelerate Deep Neural Network Training and Inference

Authors: Mostafa Mahmoud, Isak Edo, Ali Hadi Zadeh, Omar Mohamed Awad, Gennady Pekhimenko, Jorge Albericio, Andreas Moshovos

Abstract: TensorDash is a hardware level technique for enabling data-parallel MAC units to take advantage of sparsity in their input operand streams. When used to compose a hardware accelerator for deep learning, TensorDash can speedup the training process while also increasing energy efficiency. TensorDash combines a low-cost, sparse input operand interconnect comprising an 8-input multiplexer per multipli… ▽ More TensorDash is a hardware level technique for enabling data-parallel MAC units to take advantage of sparsity in their input operand streams. When used to compose a hardware accelerator for deep learning, TensorDash can speedup the training process while also increasing energy efficiency. TensorDash combines a low-cost, sparse input operand interconnect comprising an 8-input multiplexer per multiplier input, with an area-efficient hardware scheduler. While the interconnect allows a very limited set of movements per operand, the scheduler can effectively extract sparsity when it is present in the activations, weights or gradients of neural networks. Over a wide set of models covering various applications, TensorDash accelerates the training process by $1.95{\times}$ while being $1.89\times$ more energy-efficient, $1.6\times$ more energy efficient when taking on-chip and off-chip memory accesses into account. While TensorDash works with any datatype, we demonstrate it with both single-precision floating-point units and bfloat16. △ Less

Submitted 1 September, 2020; originally announced September 2020.

Generative Adversarial Stacked Autoencoders for Facial Pose Normalization and Emotion Recognition

Authors: Ariel Ruiz-Garcia, Vasile Palade, Mark Elshaw, Mariette Awad

Abstract: In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees. We accomplish this by using a novel convolutional layer that exploits both local and global spatial information, and a convolutional layer with a reduced number of parameters that exp… ▽ More In this work, we propose a novel Generative Adversarial Stacked Autoencoder that learns to map facial expressions, with up to plus or minus 60 degrees, to an illumination invariant facial representation of 0 degrees. We accomplish this by using a novel convolutional layer that exploits both local and global spatial information, and a convolutional layer with a reduced number of parameters that exploits facial symmetry. Furthermore, we introduce a generative adversarial gradual greedy layer-wise learning algorithm designed to train Adversarial Autoencoders in an efficient and incremental manner. We demonstrate the efficiency of our method and report state-of-the-art performance on several facial emotion recognition corpora, including one collected in the wild. △ Less

Submitted 19 July, 2020; originally announced July 2020.

Comments: Accepted at IJCNN 2020