Institution profile

University of Manitoba

Academic institutionnorthamerica · ca
Official website
Research library135linked papers
Opportunities0open roles
Selected work

Representative Papers

Generalization Analysis and Method for Domain Generalization for a Family of Recurrent Neural Networks

Jan 13, 2026

This work addresses the poor out-of-distribution (OOD) generalization, lack of theoretical guarantees, and limited interpretability of recurrent neural networks (RNNs) on temporal data. By modeling the post-training RNN state dynamics as a nonlinear closed-loop system, the authors introduce Koopman operator theory—applied here for the first time to RNNs—to approximate this system with a linear representation. Combining this linearization with spectral analysis, they rigorously quantify the worst-case impact of domain shift on generalization error. Based on this analysis, they derive a generalization error bound for non-i.i.d. temporal data and propose an interpretable, robust domain generalization training method. Experiments across multiple temporal tasks demonstrate that the proposed approach significantly reduces OOD generalization error and enhances model robustness to domain shifts.

1 citationsRead paper

LOCO-EPI: Leave-one-chromosome-out (LOCO) as a benchmarking paradigm for deep learning based prediction of enhancer-promoter interactions

Dec 02, 2024Applied intelligence (Boston)

Existing enhancer–promoter interaction (EPI) prediction models commonly employ random data splitting, causing leakage of homologous genomic regions across training and test sets and severely inflating estimates of generalization performance. Method: We propose leave-one-chromosome-out (LOCO) cross-validation as a new benchmarking paradigm for EPI prediction—first enforcing strict chromosomal-level separation between training and test data to eliminate genomic information leakage. Building on this, we design a hybrid deep neural network that jointly leverages k-mer sequence features and contextual modeling capabilities. Contribution/Results: Under LOCO evaluation, our model significantly outperforms state-of-the-art baselines, while most existing methods exhibit precipitous performance drops—revealing their poor generalizability. We release the first standardized EPI benchmark dataset with LOCO splits, establishing a biologically realistic evaluation framework and advancing EPI prediction research toward genuine genomic generalization.

1 citationsRead paper
Recent publications

Latest Papers