Stable clinical risk prediction against distribution shift in electronic health records
The availability of large-scale electronic health record datasets has led to the development
of artificial intelligence (AI) methods for clinical risk prediction that help improve patient care …
of artificial intelligence (AI) methods for clinical risk prediction that help improve patient care …
Mining Stable Preferences: Adaptive Modality Decorrelation for Multimedia Recommendation
Multimedia content is of predominance in the modern Web era. Many recommender models
have been proposed to investigate how users interact with items which are represented in …
have been proposed to investigate how users interact with items which are represented in …
Deep stable multi-interest learning for out-of-distribution sequential recommendation
Recently, multi-interest models, which extract interests of a user as multiple representation
vectors, have shown promising performances for sequential recommendation. However …
vectors, have shown promising performances for sequential recommendation. However …
Fairness without Demographics through Learning Graph of Gradients
Machine learning systems are notoriously prone to biased predictions about certain
demographic groups, leading to algorithmic fairness issues. Due to privacy concerns and …
demographic groups, leading to algorithmic fairness issues. Due to privacy concerns and …
Multi-Cause Learning for Diagnosis Prediction
Abstract Recently, Electronic Health Records (EHR) have become valuable for enhancing
diagnosis prediction. Despite the effectiveness of existing deep learning based methods …
diagnosis prediction. Despite the effectiveness of existing deep learning based methods …