4 papers
Guided Uncertainty-Aware Robust Domain Transfer
Xin Xiong, Zijian Guo, Tianxi Cai
Artificial intelligence models deployed as clinical decision support tools often suffer substantial performance degradation over time and across institutions due to covariate shift…
Adversarial Drift-Aware Predictive Transfer: Toward Durable Clinical AI
Xin Xiong, Zijian Guo, Haobo Zhu +4
Clinical AI systems frequently suffer performance decay post-deployment due to temporal data shifts, such as evolving populations, diagnostic coding updates (e.g., ICD-9 to ICD-10)…
Domain Adaptation Optimized for Robustness in Mixture Populations
Keyao Zhan, Xin Xiong, Zijian Guo +2
While domain adaptation methods address data shifts, most assume target populations align with at least one source population, neglecting mixtures that combine sources influenced b…
Guided Adversarial Robust Transfer Learning with Source Mixing
Xin Xiong, Zijian Guo, Tianxi Cai
Transfer learning is a critical technique that enables the application of knowledge gained from existing tasks or domains to improve performance on a new one, reducing the need for…