# CoMatch: Semi-supervised Learning with Contrastive Graph Regularization

arXiv: https://arxiv.org/abs/2011.11183 · HTML: https://mlsanity.com/paper/2011.11183/

## Key facts

- Cited by 167 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 30 of 167)

- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learning](https://mlsanity.com/paper/2301.10921/) (2023)
- [SimMatch: Semi-supervised Learning with Similarity Matching](https://mlsanity.com/paper/2203.06915/) (2022)
- [USB: A Unified Semi-supervised Learning Benchmark for Classification](https://mlsanity.com/paper/2208.07204/) (2022)
- [PromptCAL: Contrastive Affinity Learning via Auxiliary Prompts for Generalized Novel Category Discovery](https://mlsanity.com/paper/2212.05590/) (2022)
- [Debiased Learning from Naturally Imbalanced Pseudo-Labels](https://mlsanity.com/paper/2201.01490/) (2022)
- [Contrastive Semi-supervised Learning for Underwater Image Restoration via Reliable Bank](https://mlsanity.com/paper/2303.09101/) (2023)
- [Debiased Self-Training for Semi-Supervised Learning](https://mlsanity.com/paper/2202.07136/) (2022)
- [Class-Aware Contrastive Semi-Supervised Learning](https://mlsanity.com/paper/2203.02261/) (2022)
- [UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2410.10777/) (2024)
- [DASO: Distribution-Aware Semantics-Oriented Pseudo-label for Imbalanced Semi-Supervised Learning](https://mlsanity.com/paper/2106.05682/) (2021)
- [Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels](https://mlsanity.com/paper/2302.10586/) (2023)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.10026/) (2022)
- [OpenCon: Open-world Contrastive Learning](https://mlsanity.com/paper/2208.02764/) (2022)
- [Logic-induced Diagnostic Reasoning for Semi-supervised Semantic Segmentation](https://mlsanity.com/paper/2308.12595/) (2023)
- [SPACE-2: Tree-Structured Semi-Supervised Contrastive Pre-training for Task-Oriented Dialog Understanding](https://mlsanity.com/paper/2209.06638/) (2022)
- [Unsupervised Selective Labeling for More Effective Semi-Supervised Learning](https://mlsanity.com/paper/2110.03006/) (2021)
- [Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data](https://mlsanity.com/paper/2303.11066/) (2023)
- [CiPR: An Efficient Framework with Cross-instance Positive Relations for Generalized Category Discovery](https://mlsanity.com/paper/2304.06928/) (2023)
- [Towards Graph Contrastive Learning: A Survey and Beyond](https://mlsanity.com/paper/2405.11868/) (2024)
- [NP-Match: When Neural Processes meet Semi-Supervised Learning](https://mlsanity.com/paper/2207.01066/) (2022)
- [ConMatch: Semi-Supervised Learning with Confidence-Guided Consistency Regularization](https://mlsanity.com/paper/2208.08631/) (2022)
- [Learning to Defer with Limited Expert Predictions](https://mlsanity.com/paper/2304.07306/) (2023)
- [Contrastive Regularization for Semi-Supervised Learning](https://mlsanity.com/paper/2201.06247/) (2022)
- [Interpolation-based Contrastive Learning for Few-Label Semi-Supervised Learning](https://mlsanity.com/paper/2202.11915/) (2022)
- [IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization](https://mlsanity.com/paper/2308.13168/) (2023)
- [MutexMatch: Semi-Supervised Learning with Mutex-Based Consistency Regularization](https://mlsanity.com/paper/2203.14316/) (2022)
- [PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learning](https://mlsanity.com/paper/2201.08984/) (2022)
- [Semi-supervised learning made simple with self-supervised clustering](https://mlsanity.com/paper/2306.07483/) (2023)

## Abstract (arXiv)

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.