# AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergence

arXiv: https://arxiv.org/abs/2011.11779 · HTML: https://mlsanity.com/paper/2011.11779/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Nov 2020.

## Built on by (most cited first, 22 of 22)

- [Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/2208.09910/) (2022)
- [Revisiting Consistency Regularization for Semi-Supervised Learning](https://mlsanity.com/paper/2112.05825/) (2021)
- [Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data](https://mlsanity.com/paper/2303.11066/) (2023)
- [FisherMatch: Semi-Supervised Rotation Regression via Entropy-based Filtering](https://mlsanity.com/paper/2203.15765/) (2022)
- [Credal Self-Supervised Learning](https://mlsanity.com/paper/2106.11853/) (2021)
- [Towards Semi-supervised Learning with Non-random Missing Labels](https://mlsanity.com/paper/2308.08872/) (2023)
- [MaxMatch: Semi-Supervised Learning with Worst-Case Consistency](https://mlsanity.com/paper/2209.12611/) (2022)
- [Quality-agnostic Image Captioning to Safely Assist People with Vision Impairment](https://mlsanity.com/paper/2304.14623/) (2023)
- [RelationMatch: Matching In-batch Relationships for Semi-supervised Learning](https://mlsanity.com/paper/2305.10397/) (2023)
- [MultiMatch: Multi-task Learning for Semi-supervised Domain Generalization](https://mlsanity.com/paper/2208.05853/) (2022)
- [RDA: Reciprocal Distribution Alignment for Robust Semi-supervised Learning](https://mlsanity.com/paper/2208.04619/) (2022)
- [SEAL: Simultaneous Label Hierarchy Exploration And Learning](https://mlsanity.com/paper/2304.13374/) (2023)
- [OTMatch: Improving Semi-Supervised Learning with Optimal Transport](https://mlsanity.com/paper/2310.17455/) (2023)
- [LaplaceNet: A Hybrid Graph-Energy Neural Network for Deep Semi-Supervised Classification](https://mlsanity.com/paper/2106.04527/) (2021)
- [Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification](https://mlsanity.com/paper/2304.12492/) (2023)
- [Towards the Causal Complete Cause of Multi-Modal Representation Learning](https://mlsanity.com/paper/2407.14058/) (2024)
- [Okapi: Generalising Better by Making Statistical Matches Match](https://mlsanity.com/paper/2211.05236/) (2022)
- [Pushing the Envelope for Depth-Based Semi-Supervised 3D Hand Pose Estimation with Consistency Training](https://mlsanity.com/paper/2303.15147/) (2023)
- [Depth-Guided Semi-Supervised Instance Segmentation](https://mlsanity.com/paper/2406.17413/) (2024)
- [Towards Modality-agnostic Label-efficient Segmentation with Entropy-Regularized Distribution Alignment](https://mlsanity.com/paper/2408.16520/) (2024)
- [Smooth Pseudo-Labeling](https://mlsanity.com/paper/2405.14313/) (2024)
- [Semi-Supervised 360 Layout Estimation with Panoramic Collaborative Perturbations](https://mlsanity.com/paper/2503.01114/) (2025)

## Abstract (arXiv)

Semi-supervised learning (SSL) is a key approach toward more data-efficient machine learning by jointly leverage both labeled and unlabeled data. We propose AlphaMatch, an efficient SSL method that leverages data augmentations, by efficiently enforcing the label consistency between the data points and the augmented data derived from them. Our key technical contribution lies on: 1) using alpha-divergence to prioritize the regularization on data with high confidence, achieving a similar effect as FixMatch but in a more flexible fashion, and 2) proposing an optimization-based, EM-like algorithm to enforce the consistency, which enjoys better convergence than iterative regularization procedures used in recent SSL methods such as FixMatch, UDA, and MixMatch. AlphaMatch is simple and easy to implement, and consistently outperforms prior arts on standard benchmarks, e.g. CIFAR-10, SVHN, CIFAR-100, STL-10. Specifically, we achieve 91.3% test accuracy on CIFAR-10 with just 4 labelled data per class, substantially improving over the previously best 88.7% accuracy achieved by FixMatch.