Selected work

Representative Papers

ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning

Aug 10, 2026

This work addresses the critical reliability challenge in deep classification known as “high-confidence yet wrong” (JCW) predictions, which undermine abstention and human-in-the-loop mechanisms. It proposes the first training-stage formulation of trustworthy classification as a chance-constrained empirical risk minimization problem, directly bounding the JCW probability by a user-specified risk budget α via a conservative smooth inner approximation. This approach yields a theoretically sound smooth surrogate that enables rigorously certified control over JCW risk. Empirical evaluations demonstrate that the proposed ReliableNet consistently adheres to the prescribed JCW budget across four tabular and two image datasets, achieves the lowest empirical JCW under distribution shift, and excels in accuracy, coverage, calibration, and selective prediction performance.

0 citationsRead paper

RRaPINNs: Residual Risk-Aware Physics Informed Neural Networks

Nov 23, 2025

Physics-informed neural networks (PINNs) minimize the mean residual, which can obscure localized large errors and compromise solution reliability. To address this, we propose a residual risk-aware training framework that explicitly targets tail residual control. Our method introduces conditional value-at-risk (CVaR) and mean excess (ME) surrogate penalties, establishing a theoretical connection between risk-sensitive optimization and chance-constrained learning. We further design three mechanisms: persistent hard-point replay, local risk budgeting, and multi-objective risk modeling—enabling explicit trade-offs between accuracy and tail robustness. Experiments on Burgers, heat, Korteweg–de Vries (KdV), and Poisson equations demonstrate that our approach reduces tail errors by up to 57%, maintains or improves mean error, enhances training stability, and effectively handles discontinuous solutions.

0 citationsRead paper

Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments

Nov 20, 2025

This study systematically exposes fundamental limitations of scalarization-based methods in multi-objective reinforcement learning (MORL) with discrete action and observation spaces: poor Pareto-front coverage, low robustness, and strong dependence on environmental properties and front geometry. To address these issues, we propose an inner-loop multi-policy architecture and comparatively evaluate three representative approaches—linear scalarization, Chebyshev scalarization, and non-scalarized Pareto Q-learning—under both outer-loop single-policy and inner-loop multi-policy paradigms. Results demonstrate that Pareto Q-learning significantly improves solution-set diversity and stability over scalarized methods. Moreover, the inner-loop multi-policy design effectively mitigates scalarization’s sensitivity to weight selection and susceptibility to local optima. Our empirical analysis provides both a novel methodological paradigm and rigorous evidence for developing robust, scalable MORL algorithms.

0 citationsRead paper

A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithms

Nov 20, 2025

This study investigates how decision transformers (DTs) compare to conventional offline reinforcement learning (RL) algorithms—specifically conservative Q-learning (CQL) and implicit Q-learning (IQL)—under varying reward densities (dense vs. sparse) in the ANT continuous-control benchmark. Method: We conduct a systematic, controlled empirical evaluation across uniformly configured offline datasets of varying quality and reward sparsity. Contribution/Results: We find that DTs exhibit remarkable robustness to reward density shifts: they outperform both CQL and IQL in sparse-reward regimes and under medium-quality offline data, achieving higher policy performance, greater stability, and lower evaluation variance. In contrast, IQL excels in dense-reward settings, while CQL demonstrates superior overall robustness across diverse conditions. Crucially, this work provides the first empirical evidence that sequence modeling—via autoregressive action prediction—confers distinct advantages in low signal-to-noise-ratio feedback environments. These findings offer principled guidance for reward-structure-aware algorithm selection and design in offline RL.

0 citationsRead paper

Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification, An Interpretable Multi-Omics Approach

Mar 29, 2025

To address the challenge of precise classification across 31 cancer types and interpretable biomarker discovery, this paper proposes GKAN—the first Graph-structured Kolmogorov–Arnold Neural Network integrating multi-omics data (mRNA, miRNA, DNA methylation) with protein–protein interaction (PPI) networks. Innovatively, it embeds the Kolmogorov–Arnold representation theorem into graph neural architecture to enable univariate interpretability. A systematic pipeline combines multi-stage dimensionality reduction (DESeq2/LIMMA/LASSO) with GO/KEGG enrichment analysis, uncovering conserved regulatory roles of phosphatidylinositol-binding proteins and sphingolipid metabolism pathways across cancers. Evaluated on TCGA’s 31-cancer cohort, GKAN achieves 96.28% classification accuracy, with standard deviation reduced by 1.58–7.30 percentage points versus CNN- and GNN-based baselines. Furthermore, it identifies experimentally validated pan-cancer biomarkers, establishing both high predictive performance and biological interpretability.

0 citationsRead paper

Recent publications

Latest Papers

ReliableNet: A Chance-Constrained Approach to Trustworthy Classification in Deep Learning

Aug 10, 2026

This work addresses the critical reliability challenge in deep classification known as “high-confidence yet wrong” (JCW) predictions, which undermine abstention and human-in-the-loop mechanisms. It proposes the first training-stage formulation of trustworthy classification as a chance-constrained empirical risk minimization problem, directly bounding the JCW probability by a user-specified risk budget α via a conservative smooth inner approximation. This approach yields a theoretically sound smooth surrogate that enables rigorously certified control over JCW risk. Empirical evaluations demonstrate that the proposed ReliableNet consistently adheres to the prescribed JCW budget across four tabular and two image datasets, achieves the lowest empirical JCW under distribution shift, and excels in accuracy, coverage, calibration, and selective prediction performance.

0 citationsRead paper

RRaPINNs: Residual Risk-Aware Physics Informed Neural Networks

Nov 23, 2025

Physics-informed neural networks (PINNs) minimize the mean residual, which can obscure localized large errors and compromise solution reliability. To address this, we propose a residual risk-aware training framework that explicitly targets tail residual control. Our method introduces conditional value-at-risk (CVaR) and mean excess (ME) surrogate penalties, establishing a theoretical connection between risk-sensitive optimization and chance-constrained learning. We further design three mechanisms: persistent hard-point replay, local risk budgeting, and multi-objective risk modeling—enabling explicit trade-offs between accuracy and tail robustness. Experiments on Burgers, heat, Korteweg–de Vries (KdV), and Poisson equations demonstrate that our approach reduces tail errors by up to 57%, maintains or improves mean error, enhances training stability, and effectively handles discontinuous solutions.

0 citationsRead paper

Limitations of Scalarisation in MORL: A Comparative Study in Discrete Environments

Nov 20, 2025

This study systematically exposes fundamental limitations of scalarization-based methods in multi-objective reinforcement learning (MORL) with discrete action and observation spaces: poor Pareto-front coverage, low robustness, and strong dependence on environmental properties and front geometry. To address these issues, we propose an inner-loop multi-policy architecture and comparatively evaluate three representative approaches—linear scalarization, Chebyshev scalarization, and non-scalarized Pareto Q-learning—under both outer-loop single-policy and inner-loop multi-policy paradigms. Results demonstrate that Pareto Q-learning significantly improves solution-set diversity and stability over scalarized methods. Moreover, the inner-loop multi-policy design effectively mitigates scalarization’s sensitivity to weight selection and susceptibility to local optima. Our empirical analysis provides both a novel methodological paradigm and rigorous evidence for developing robust, scalable MORL algorithms.

0 citationsRead paper

A Comparison Between Decision Transformers and Traditional Offline Reinforcement Learning Algorithms

Nov 20, 2025

This study investigates how decision transformers (DTs) compare to conventional offline reinforcement learning (RL) algorithms—specifically conservative Q-learning (CQL) and implicit Q-learning (IQL)—under varying reward densities (dense vs. sparse) in the ANT continuous-control benchmark. Method: We conduct a systematic, controlled empirical evaluation across uniformly configured offline datasets of varying quality and reward sparsity. Contribution/Results: We find that DTs exhibit remarkable robustness to reward density shifts: they outperform both CQL and IQL in sparse-reward regimes and under medium-quality offline data, achieving higher policy performance, greater stability, and lower evaluation variance. In contrast, IQL excels in dense-reward settings, while CQL demonstrates superior overall robustness across diverse conditions. Crucially, this work provides the first empirical evidence that sequence modeling—via autoregressive action prediction—confers distinct advantages in low signal-to-noise-ratio feedback environments. These findings offer principled guidance for reward-structure-aware algorithm selection and design in offline RL.

0 citationsRead paper

Graph Kolmogorov-Arnold Networks for Multi-Cancer Classification and Biomarker Identification, An Interpretable Multi-Omics Approach

Mar 29, 2025

To address the challenge of precise classification across 31 cancer types and interpretable biomarker discovery, this paper proposes GKAN—the first Graph-structured Kolmogorov–Arnold Neural Network integrating multi-omics data (mRNA, miRNA, DNA methylation) with protein–protein interaction (PPI) networks. Innovatively, it embeds the Kolmogorov–Arnold representation theorem into graph neural architecture to enable univariate interpretability. A systematic pipeline combines multi-stage dimensionality reduction (DESeq2/LIMMA/LASSO) with GO/KEGG enrichment analysis, uncovering conserved regulatory roles of phosphatidylinositol-binding proteins and sphingolipid metabolism pathways across cancers. Evaluated on TCGA’s 31-cancer cohort, GKAN achieves 96.28% classification accuracy, with standard deviation reduced by 1.58–7.30 percentage points versus CNN- and GNN-based baselines. Furthermore, it identifies experimentally validated pan-cancer biomarkers, establishing both high predictive performance and biological interpretability.

0 citationsRead paper