Institution profile

Michigan State University

Academic institutionnorthamerica · us
Official website
Research library718linked papers
Opportunities0open roles
Selected work

Representative Papers

Robust Unsupervised Multi-task and Transfer Learning on Gaussian Mixture Models

Sep 30, 2022

This paper addresses unsupervised multi-task and transfer learning for Gaussian mixture models (GMMs), tackling challenges including unknown inter-task parameter structural similarity, presence of outlier tasks, and initialization misalignment. We propose the first robust multi-task learning framework for GMMs with theoretical guarantees, featuring: (1) a weighted EM algorithm resilient to outlier tasks; (2) dual alignment—simultaneous alignment in both label space and parameter space—to mitigate initialization sensitivity; and (3) adaptive estimation of task similarity coupled with a transfer-generalization design. We establish minimax-optimal convergence rates for both parameter estimation error and misclustering error. Extensive experiments on synthetic and real-world datasets demonstrate substantial improvements over single-task baselines, yielding enhanced clustering stability and more accurate parameter estimation.

2 citationsRead paper

Enhancing Generalization in Evolutionary Feature Construction for Symbolic Regression Through Vicinal Jensen Gap Minimization

Feb 02, 2026IEEE Transactions on Evolutionary Computation

This work addresses the limited generalization of genetic programming in symbolic regression due to overfitting. The authors propose a novel evolutionary feature construction method based on neighborhood risk decomposition, which, for the first time, incorporates the neighborhood Jensen gap as a regularization term to jointly optimize empirical risk and the Jensen gap. To enhance robustness, the approach integrates dynamic regularization strength adjustment, manifold intrusion detection, and noise perturbation mechanisms, effectively mitigating the generation of unrealistic samples caused by data augmentation. Extensive experiments on 58 benchmark datasets demonstrate that the proposed method outperforms existing complexity-controlling metrics and significantly improves symbolic regression performance compared to 15 state-of-the-art machine learning algorithms.

1 citationsRead paper

Is Moral Self-correction An Innate Capability of Large Language Models? A Mechanistic Analysis to Self-correction

Oct 27, 2024arXiv.org

This work investigates whether large language models (LLMs) possess intrinsic moral self-correction capabilities. We propose the “Self-Discrimination” validation framework, integrating hidden-state intervention analysis, natural-language weak-evidence perturbation, multi-component ablation studies, and task-based evaluation to systematically dissect the interplay among chain-of-thought reasoning, external feedback, and instruction prompting in moral representation correction. Our mechanistic analysis establishes, for the first time: (1) moral self-correction is not an inherent property of pretraining; (2) internal knowledge and external feedback exhibit negative interaction; (3) while models can revise erroneous outputs, they lack reliable discrimination between high- and low-quality responses; and (4) no universally optimal correction strategy exists. The core contributions lie in empirically demonstrating the non-innateness, mechanism-dependence, and evaluation fragility of moral correction—providing novel empirical foundations for trustworthy AI alignment.

1 citationsRead paper

NervePool: A Simplicial Pooling Layer

May 10, 2023arXiv.org

Existing graph pooling methods fail to preserve higher-order combinatorial and topological consistency when applied to simplicial complexes—topological data structures capable of encoding high-order relational information. Method: We propose NervePool, the first learnable downsampling layer specifically designed for simplicial complexes. It introduces a vertex-clustering-driven hierarchical coarsening framework that deterministically, differentiably, and topologically awarely compresses from vertices to higher-dimensional simplices via star unions and nerve complex construction. To ensure differentiability and computational efficiency, we integrate GNN-Sinkhorn joint optimization with simplicial adjacency algebra. Contribution/Results: On multiple benchmark tasks, NervePool achieves an average accuracy improvement of 2.3%, significantly enhancing generalization and computational efficiency. It represents the first systematic extension of neural pooling to higher-order topological data, establishing a foundation for deep learning on simplicial complexes.

1 citationsRead paper
Recent publications

Latest Papers