Enhancing Contrastive Learning with Variable Similarity

NeurIPSSpotlight2025

Authors: Haowen Cui, Shuo Chen, Jun Li, Jian Yang
Venue: NeurIPS 2025
Track: Spotlight

TL;DR

Contrastive learning has achieved remarkable success in self-supervised learning by pretraining a generalizable feature representation based on the augmentation invariance…

Opening excerpt from the authors’ abstract. source

Read the paper

OpenReview

Topics

self-supervised contrastive pretraining

← All NeurIPS 2025 Spotlight papers · Browse the whole archive