mlsanityData to 7 Oct 2026

RelationMatch: Matching In-batch Relationships for Semi-supervised Learning

arXiv 2305.10397 ↗First posted 17 May 2023cs.LG cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning has emerged as a pivotal approach for leveraging scarce labeled data alongside abundant unlabeled data. Despite significant progress, prevailing SSL methods predominantly enforce consistency between different augmented views of individual samples, thereby overlooking the rich relational structure inherent within a mini-batch. In this paper, we present RelationMatch, a novel SSL framework that explicitly enforces in-batch relational consistency through a Matrix Cross-Entropy (MCE) loss function. The proposed MCE loss is rigorously derived from both matrix analysis and information geometry perspectives, ensuring theoretical soundness and practical efficacy. Extensive empirical evaluations on standard benchmarks, including a notable 15.21% accuracy improvement over FlexMatch on STL-10, demonstrate that RelationMatch not only advances state-of-the-art performance but also provides a principled foundation for incorporating relational cues in SSL.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 32 of its 44 references that are in the map. First posted on arXiv 17 May 2023.

Builds on

32 of 44 references.

References · 32

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  4. 2016Wide Residual Networkscited by 3,057
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2019Similarity of Neural Network Representations Revisitedcited by 1,695
  7. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  8. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  9. 2019Contrastive Multiview Codingcited by 1,297
  10. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  11. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  12. 2019When Does Label Smoothing Help?cited by 985
20 more
  1. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  2. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 537
  3. 2020Meta Pseudo Labelscited by 372
  4. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  5. 2019On Mutual Information Maximization for Representation Learningcited by 315
  6. 2015Semi-Supervised Learning with Ladder Networkscited by 246
  7. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  8. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  9. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  10. 2022Contrastive and Non-Contrastive Self-Supervised Learning Recover Global and Local Spectral Embedding Methodscited by 146
  11. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  12. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  13. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  14. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  15. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  16. 2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
  17. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  18. 2020AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergencecited by 22
  19. 2022MaxMatch: Semi-Supervised Learning with Worst-Case Consistencycited by 9
  20. 2023SEAL: Simultaneous Label Hierarchy Exploration And Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2023: 4; 2024: 3; 2025: 1.

8 papers.

  1. 2024Diff-eRank: A Novel Rank-Based Metric for Evaluating Large Language Modelscited by 35
  2. 2023Matrix Information Theory for Self-Supervised Learningcited by 21
  3. 2023Information Flow in Self-Supervised Learningcited by 16
  4. 2023Understanding Grokking Through A Robustness Viewpointcited by 10
  5. 2023OTMatch: Improving Semi-Supervised Learning with Optimal Transportcited by 6
  6. 2024Unveiling the Dynamics of Information Interplay in Supervised Learningcited by 3
  7. 2024Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Trainingcited by 1
  8. 2025Information-Theoretic Perspectives on Optimizerscited by 0