Hoda Eldardiry, Ismini Lourentzou, Muntasir Wahed, Afrina Tabassum

Abstract

One of the challenges in contrastive learning is the selection of appropriate \textit{hard negative} examples, in the absence of label information. Random sampling or importance sampling methods based on feature similarity often lead to sub-optimal performance. In this work, we introduce UnReMix, a hard negative sampling strategy that takes into account anchor similarity, model uncertainty and representativeness. Experimental results on several benchmarks show that UnReMix improves negative sample selection, and subsequently downstream performance when compared to state-of-the-art contrastive learning methods.

People

Ismini Lourentzou


Afrina Tabassum


Hoda Eldardiry


Muntasir Wahed


Publication Details

Date of publication:
June 2, 2022
Journal:
Cornell University
Publication note:

Afrina Tabassum, Muntasir Wahed, Hoda Eldardiry, Ismini Lourentzou: Hard Negative Sampling Strategies for Contrastive Representation Learning. CoRR abs/2206.01197 (2022)