mlsanityData to 7 Oct 2026

Graph Barlow Twins: A self-supervised representation learning framework for graphs

arXiv 2106.02466 ↗First posted 4 Jun 2021cs.LGcited by 85

Not on the map. Why?

Abstract (arXiv)

The self-supervised learning (SSL) paradigm is an essential exploration area, which tries to eliminate the need for expensive data labeling. Despite the great success of SSL methods in computer vision and natural language processing, most of them employ contrastive learning objectives that require negative samples, which are hard to define. This becomes even more challenging in the case of graphs and is a bottleneck for achieving robust representations. To overcome such limitations, we propose a framework for self-supervised graph representation learning - Graph Barlow Twins, which utilizes a cross-correlation-based loss function instead of negative samples. Moreover, it does not rely on non-symmetric neural network architectures - in contrast to state-of-the-art self-supervised graph representation learning method BGRL. We show that our method achieves as competitive results as the best self-supervised methods and fully supervised ones while requiring fewer hyperparameters and substantially shorter computation time (ca. 30 times faster than BGRL).

Key facts. Cited by 85 papers in the map (data through 7 Oct 2026). Builds on 23 of its 34 references that are in the map. First posted on arXiv 4 Jun 2021.

Builds on

23 of 34 references.

References · 23

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Graph Attention Networkscited by 8,854
  3. 2017Inductive Representation Learning on Large Graphscited by 6,284
  4. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  5. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  6. 2019Fast Graph Representation Learning with PyTorch Geometriccited by 2,414
  7. 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,148
  8. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  9. 2021Barlow Twins: Self-Supervised Learning via Redundancy Reductioncited by 1,818
  10. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  11. 2016Variational Graph Auto-Encoderscited by 1,373
  12. 2020Graph Contrastive Learning with Augmentationscited by 1,203
11 more
  1. 2018Deep Graph Infomaxcited by 1,101
  2. 2015Image-based Recommendations on Styles and Substitutescited by 702
  3. 2016End-to-end Optimized Image Compressioncited by 673
  4. 2015LINE: Large-scale Information Network Embeddingcited by 582
  5. 2020Deep Graph Contrastive Representation Learningcited by 535
  6. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  7. 2020Wiki-CS: A Wikipedia-Based Benchmark for Graph Neural Networkscited by 253
  8. 2017Predicting multicellular function through multi-layer tissue networkscited by 138
  9. 2019Micro-Batch Training with Batch-Channel Normalization and Weight Standardizationcited by 45
  10. 2021A Note on Connecting Barlow Twins with Negative-Sample-Free Contrastive Learningcited by 26
  11. 2020Self-supervised Graph Representation Learning via Bootstrappingcited by 8

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 4; 2022: 20; 2023: 13; 2024: 28; 2025: 13; 2026: 7.

85 papers.

Sort:

By area:

  1. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  2. 2021An Empirical Study of Graph Contrastive Learningcited by 113
  3. 2021Augmentation-Free Self-Supervised Learning on Graphscited by 94
  4. 2022Rethinking and Scaling Up Graph Contrastive Learning: An Extremely Efficient Approach with Group Discriminationcited by 67
  5. 2022Graph Data Augmentation for Graph Machine Learning: A Surveycited by 61
  6. 2022Simple Contrastive Graph Clusteringcited by 56
  7. 2022Spectral Feature Augmentation for Graph Contrastive Learning and Beyondcited by 49
  8. 2022Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structurecited by 43
  9. 2022COSTA: Covariance-Preserving Feature Augmentation for Graph Contrastive Learningcited by 38
  10. 2022Spectral Augmentation for Self-Supervised Learning on Graphscited by 38
  11. 2024Towards Graph Contrastive Learning: A Survey and Beyondcited by 26
  12. 2022ImGCL: Revisiting Graph Contrastive Learning on Imbalanced Node Classificationcited by 21
38 more
  1. 2022Mixed Graph Contrastive Network for Semi-Supervised Node Classificationcited by 21
  2. 2023Embedding in Recommender Systems: A Surveycited by 19
  3. 2023HomoGCL: Rethinking Homophily in Graph Contrastive Learningcited by 18
  4. 2022Graph Soft-Contrastive Learning via Neighborhood Rankingcited by 16
  5. 2024SeBot: Structural Entropy Guided Multi-View Contrastive Learning for Social Bot Detectioncited by 16
  6. 2024GAugLLM: Improving Graph Contrastive Learning for Text-Attributed Graphs with Large Language Modelscited by 16
  7. 2022Link Prediction with Non-Contrastive Learningcited by 11
  8. 2022Data Augmentation on Graphs: A Technical Surveycited by 10
  9. 2023PTGB: Pre-Train Graph Neural Networks for Brain Network Analysiscited by 10
  10. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  11. 2022Unsupervised Network Embedding Beyond Homophilycited by 7
  12. 2023MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learningcited by 7
  13. 2024Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspectivecited by 7
  14. 2023Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learningcited by 6
  15. 2024Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learningcited by 6
  16. 2022Omni-Granular Ego-Semantic Propagation for Self-Supervised Graph Representation Learningcited by 5
  17. 2023Graph Contrastive Learning under Heterophily via Graph Filterscited by 5
  18. 2023CARL-G: Clustering-Accelerated Representation Learning on Graphscited by 5
  19. 2024Negative-Free Self-Supervised Gaussian Embedding of Graphscited by 5
  20. 2025Rethinking Graph Contrastive Learning through Relative Similarity Preservationcited by 5
  21. 2025Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applicationscited by 5
  22. 2023Spectral-Aware Augmentation for Enhanced Graph Representation Learningcited by 4
  23. 2024GraphFM: A Comprehensive Benchmark for Graph Foundation Modelcited by 4
  24. 2024LATEX-GCL: Large Language Models (LLMs)-Based Data Augmentation for Text-Attributed Graph Contrastive Learningcited by 4
  25. 2021Jointly Learnable Data Augmentations for Self-Supervised GNNscited by 3
  26. 2022Semi-Supervised Heterogeneous Graph Learning with Multi-level Data Augmentationcited by 3
  27. 2024WERank: Towards Rank Degradation Prevention for Self-Supervised Learning Using Weight Regularizationcited by 3
  28. 2024Overcoming Pitfalls in Graph Contrastive Learning Evaluation: Toward Comprehensive Benchmarkscited by 3
  29. 2024Representation learning in multiplex graphs: Where and how to fuse information?cited by 3
  30. 2024Vision HgNN: An Electron-Micrograph is Worth Hypergraph of Hypernodescited by 3
  31. 2025InfoNCE is a Free Lunch for Semantically guided Graph Contrastive Learningcited by 3
  32. 2025Str-GCL: Structural Commonsense Driven Graph Contrastive Learningcited by 3
  33. 2022FastGCL: Fast Self-Supervised Learning on Graphs via Contrastive Neighborhood Aggregationcited by 2
  34. 2025Principled Data Augmentation for Learning to Solve Quadratic Programming Problemscited by 2
  35. 2021Barlow Graph Auto-Encoder for Unsupervised Network Embeddingcited by 1
  36. 2022KG-NSF: Knowledge Graph Completion with a Negative-Sample-Free Approachcited by 1
  37. 2023Structure-Aware Group Discrimination with Adaptive-View Graph Encoder: A Fast Graph Contrastive Learning Frameworkcited by 1
  38. 2023Towards Aligned Canonical Correlation Analysis: Preliminary Formulation and Proof-of-Concept Resultscited by 1

50 most cited of 85 All 85 (JSON)