Do More Negative Samples Necessarily Hurt In Contrastive Learning?

Pranjal Awasthi · Nishanth Dikkala · Pritish Kamath

Hall E #502

Keywords: [ DL: Other Representation Learning ] [ MISC: Representation Learning ] [ DL: Theory ] [ T: Deep Learning ] [ MISC: Unsupervised and Semi-supervised Learning ] [ DL: Self-Supervised Learning ]


Recent investigations in noise contrastive estimation suggest, both empirically as well as theoretically, that while having more negative samples'' in the contrastive loss improves downstream classification performance initially, beyond a threshold, it hurts downstream performance due to acollision-coverage'' trade-off. But is such a phenomenon inherent in contrastive learning?We show in a simple theoretical setting, where positive pairs are generated by sampling from the underlying latent class (introduced by Saunshi et al. (ICML 2019)), that the downstream performance of the representation optimizing the (population) contrastive loss in fact does not degrade with the number of negative samples. Along the way, we give a structural characterization of the optimal representation in our framework, for noise contrastive estimation. We also provide empirical support for our theoretical results on CIFAR-10 and CIFAR-100 datasets.

Chat is not available.