mlsanityData to 14 Oct 2026

Uncovering the Structural Fairness in Graph Contrastive Learning

arXiv 2210.03011 ↗First posted 6 Oct 2022cs.LG cs.SIcited by 29

Not on the map. Why?

Abstract (arXiv)

Recent studies show that graph convolutional network (GCN) often performs worse for low-degree nodes, exhibiting the so-called structural unfairness for graphs with long-tailed degree distributions prevalent in the real world. Graph contrastive learning (GCL), which marries the power of GCN and contrastive learning, has emerged as a promising self-supervised approach for learning node representations. How does GCL behave in terms of structural fairness? Surprisingly, we find that representations obtained by GCL methods are already fairer to degree bias than those learned by GCN. We theoretically show that this fairness stems from intra-community concentration and inter-community scatter properties of GCL, resulting in a much clear community structure to drive low-degree nodes away from the community boundary. Based on our theoretical analysis, we further devise a novel graph augmentation method, called GRAph contrastive learning for DEgree bias (GRADE), which applies different strategies to low- and high-degree nodes. Extensive experiments on various benchmarks and evaluation protocols validate the effectiveness of the proposed method.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 31 of its 45 references that are in the map. First posted on arXiv 6 Oct 2022.

Builds on

31 of 45 references.

References · 31

  1. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  4. 2017Graph Attention Networkscited by 8,923
  5. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  6. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  7. 2017Inductive Representation Learning on Large Graphscited by 6,320
  8. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  9. 2019A Comprehensive Survey on Graph Neural Networkscited by 2,919
  10. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
  11. 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
  12. 2019Simplifying Graph Convolutional Networkscited by 1,477
19 more
  1. 2019Contrastive Multiview Codingcited by 1,301
  2. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
  3. 2020Graph Contrastive Learning with Augmentationscited by 1,208
  4. 2018Deep Graph Infomaxcited by 1,106
  5. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  7. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  8. 2020Contrastive Multi-View Representation Learning on Graphscited by 652
  9. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 584
  10. 2020Deep Graph Contrastive Representation Learningcited by 539
  11. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  12. 2020GCC: Graph Contrastive Coding for Graph Neural Network Pre-Trainingcited by 463
  13. 2019InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximizationcited by 441
  14. 2021Graph Self-Supervised Learning: A Surveycited by 289
  15. 2021From Canonical Correlation Analysis to Self-supervised Graph Neural Networkscited by 141
  16. 2021Self-supervised Learning on Graphs: Contrastive, Generative,or Predictivecited by 136
  17. 2021Towards the Generalization of Contrastive Self-Supervised Learningcited by 99
  18. 2019DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classificationcited by 59
  19. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 8; 2024: 9; 2025: 10; 2026: 2.

29 papers.

Sort:

  1. 2023Data-centric Graph Learning: A Surveycited by 22
  2. 2025Uncertainty-Aware Graph Neural Networks: A Multi-Hop Evidence Fusion Approachcited by 14
  3. 2024Graph Fairness Learning under Distribution Shiftscited by 10
  4. 2024Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behaviorcited by 10
  5. 2024A Survey on Self-Supervised Graph Foundation Models: Knowledge-Based Perspectivecited by 9
  6. 2024Optimizing Long-tailed Link Prediction in Graph Neural Networks through Structure Representation Enhancementcited by 9
  7. 2023SAILOR: Structural Augmentation Based Tail Node Representation Learningcited by 6
  8. 2023Mitigating Degree Biases in Message Passing Mechanism by Utilizing Community Structurescited by 6
  9. 2024Toward Structure Fairness in Dynamic Graph Embedding: A Trend-aware Dual Debiasing Approachcited by 6
  10. 2024Node Duplication Improves Cold-start Link Predictioncited by 4
  11. 2024Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networkscited by 4
  12. 2024GETS: Ensemble Temperature Scaling for Calibration in Graph Neural Networkscited by 4
17 more
  1. 2023Towards Label Position Bias in Graph Neural Networkscited by 3
  2. 2023Equipping Federated Graph Neural Networks with Structure-aware Group Fairnesscited by 2
  3. 2023Marginal Nodes Matter: Towards Structure Fairness in Graphscited by 2
  4. 2025Fairness in Augmented Graph Learning: A Surveycited by 2
  5. 2026Benchmarking Bias Mitigation Toward Fairness Without Harm from Vision to LVLMscited by 1
  6. 2023Migrate Demographic Group For Fair GNNscited by 0
  7. 2023Understanding Community Bias Amplification in Graph Representation Learningcited by 0
  8. 2024CYCLE: Cross-Year Contrastive Learning in Entity-Linkingcited by 0
  9. 2025FairACE: Achieving Degree Fairness in Graph Neural Networks via Contrastive and Adversarial Group-Balanced Trainingcited by 0
  10. 2025Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attentioncited by 0
  11. 2025Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learningcited by 0
  12. 2025Model-Driven Graph Contrastive Learningcited by 0
  13. 2025Enhancing Contrastive Link Prediction With Edge Balancing Augmentationcited by 0
  14. 2025Understanding Fairness and Prediction Error through Subspace Decomposition and Influence Analysiscited by 0
  15. 2025Mitigating Bias in Graph Hyperdimensional Computingcited by 0
  16. 2025Exploring Topological Bias in Heterogeneous Graph Neural Networkscited by 0
  17. 2026Revisiting Positive Samples in Graph Contrastive Learning: From the Perspective of Message Passingcited by 0