RESEARCHarXiv CS.LG·26d ago
A Unified Geometric Framework for Weighted Contrastive Learning
Contrastive learning aims to preserve relational structure in sample representations by reflecting a similarity graph. This paper interprets weighted InfoNCE objectives as Distance Geometry Problems, providing a unified geometric framework and exact characterizations of optimal embeddings, revealing how class imbalance affects inter-class similarities in SupCon.
27
