Ga Wu

Self-Supervised Representation Learning as Mutual Information Maximization

2025 · arXiv (Cornell University)

Self-supervised representation learning (SSRL) has demonstrated remarkable empirical success, yet its underlying principles remain insufficiently understood. While recent works attempt to unify SSRL methods by examining their information-theoretic objectives or summarizing their heuristics for preventing …

Deep language-based critiquing for recommender systems

2019

Critiquing is a method for conversational recommendation that adapts recommendations in response to user preference feedback regarding item attributes. Historical critiquing methods were largely based on constraint- and utility-based methods for modifying recommendations w.r.t. these …