CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

TL;DR

CoMatch introduces a semi-supervised learning method that combines contrastive graph regularization with dual data representations, significantly improving accuracy and representation quality on various datasets.

Contribution

It unifies existing semi-supervised approaches with a novel contrastive graph regularization framework, enhancing pseudo-label accuracy and embedding structure.

Findings

Achieves state-of-the-art results on multiple datasets.

Significantly outperforms FixMatch on ImageNet with 1% labels.

Improves downstream task performance over supervised and self-supervised methods.

Abstract

Semi-supervised learning has been an effective paradigm for leveraging unlabeled data to reduce the reliance on labeled data. We propose CoMatch, a new semi-supervised learning method that unifies dominant approaches and addresses their limitations. CoMatch jointly learns two representations of the training data, their class probabilities and low-dimensional embeddings. The two representations interact with each other to jointly evolve. The embeddings impose a smoothness constraint on the class probabilities to improve the pseudo-labels, whereas the pseudo-labels regularize the structure of the embeddings through graph-based contrastive learning. CoMatch achieves state-of-the-art performance on multiple datasets. It achieves substantial accuracy improvements on the label-scarce CIFAR-10 and STL-10. On ImageNet with 1% labels, CoMatch achieves a top-1 accuracy of 66.0%, outperforming FixMatch by 12.6%. Furthermore, CoMatch achieves better representation learning performance on downstream tasks, outperforming both supervised learning and self-supervised learning. Code and pre-trained models are available at https://github.com/salesforce/CoMatch.