Dissecting Supervised Contrastive Learning
Proceedings of the 38th International Conference on Machine Learning, PMLR 139:3821-3830, 2021 Minimizing cross-entropy over the softmax scores of a linear map composed with a high-capacity encoder is arguably the most popular choice for training neural networks on supervised learning tasks. However...
Saved in:
Main Authors | , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
17.02.2021
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Proceedings of the 38th International Conference on Machine
Learning, PMLR 139:3821-3830, 2021 Minimizing cross-entropy over the softmax scores of a linear map composed
with a high-capacity encoder is arguably the most popular choice for training
neural networks on supervised learning tasks. However, recent works show that
one can directly optimize the encoder instead, to obtain equally (or even more)
discriminative representations via a supervised variant of a contrastive
objective. In this work, we address the question whether there are fundamental
differences in the sought-for representation geometry in the output space of
the encoder at minimal loss. Specifically, we prove, under mild assumptions,
that both losses attain their minimum once the representations of each class
collapse to the vertices of a regular simplex, inscribed in a hypersphere. We
provide empirical evidence that this configuration is attained in practice and
that reaching a close-to-optimal state typically indicates good generalization
performance. Yet, the two losses show remarkably different optimization
behavior. The number of iterations required to perfectly fit to data scales
superlinearly with the amount of randomly flipped labels for the supervised
contrastive loss. This is in contrast to the approximately linear scaling
previously reported for networks trained with cross-entropy. |
---|---|
DOI: | 10.48550/arxiv.2102.08817 |