8 papers
Shift-Invariant Attribute Scoring for Kolmogorov-Arnold Networks via Shapley Value
Wangxuan Fan, Ching Wang, Siqi Li +1
For many real-world applications, understanding feature-outcome relationships is as crucial as achieving high predictive accuracy. While traditional neural networks excel at predic…
Distributionally Robust Transfer Learning with Structurally Missing Covariates, with Application to Cross-National Cardiac Arrest Prediction
Siqi Li, Chuan Hong, Ziye Tian +9
Deploying clinical prediction models across healthcare systems often fails when key training covariates are unavailable at deployment and labeled outcomes are limited in the target…
Communication-efficient distributed hazard difference estimation for heterogeneous multi-site survival data
Ziwen Wang, Siqi Li, Marcus Eng Hock Ong +1
Multi-site collaboration can power survival models that no single hospital could fit alone, but privacy rules and protected computing environments block patient-level data sharing…
TRACER: Transfer Learning based Real-time Adaptation for Clinical Evolving Risk
Mengying Yan, Ziye Tian, Siqi Li +4
Clinical decision support tools built on electronic health records often experience performance drift due to temporal population shifts, particularly when changes in the clinical e…
SIM-Shapley: A Stable and Computationally Efficient Approach to Shapley Value Approximation
Wangxuan Fan, Siqi Li, Doudou Zhou +4
Explainable artificial intelligence (XAI) is essential for trustworthy machine learning (ML), particularly in high-stakes domains such as healthcare and finance. Shapley value (SV)…
Robust Mixture Models for Algorithmic Fairness Under Latent Heterogeneity
Siqi Li, Molei Liu, Ziye Tian +2
Standard machine learning models optimized for average performance often fail on minority subgroups and lack robustness to distribution shifts. This challenge worsens when subgroup…