← Search

Jeongheon Oh

2 accepted papers

2025

A Theoretical Framework for Preventing Class Collapse in Supervised Contrastive Learning

AISTATS 2025poster

Supervised contrastive learning (SupCL) has emerged as a prominent approach in representation learning, leveraging both supervised and self-supervised losses. However, achieving an optimal balance between these losses is challenging; failing to do so can lead to class collapse, reducing discriminati…

Cited by 0SourceScholar