Graph

Pattern recognition (psychology)

Mathematics

Semi-supervised learning

Politics

Machine learning

Supervised learning

Political science

Artificial intelligence

Set (abstract data type)

Regularization (linguistics)

Programming language

Class (philosophy)

Geometry

Constraint (computer-aided design)

Labeled data

Representation (politics)

Code (set theory)

Computer science

Theoretical computer science

Artificial neural network

Feature learning

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 [32] 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/.

CoMatch: Semi-supervised Learning with Contrastive Graph Regularization