mlsanityData to 7 Oct 2026

FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently

arXiv 2401.14702 ↗First posted 26 Jan 2024cs.LG cs.AI cs.CYcited by 8

Not on the map. Why?

Abstract (arXiv)

Fairness in Graph Convolutional Neural Networks (GCNs) becomes a more and more important concern as GCNs are adopted in many crucial applications. Societal biases against sensitive groups may exist in many real world graphs. GCNs trained on those graphs may be vulnerable to being affected by such biases. In this paper, we adopt the well-known fairness notion of demographic parity and tackle the challenge of training fair and accurate GCNs efficiently. We present an in-depth analysis on how graph structure bias, node attribute bias, and model parameters may affect the demographic parity of GCNs. Our insights lead to FairSample, a framework that jointly mitigates the three types of biases. We employ two intuitive strategies to rectify graph structures. First, we inject edges across nodes that are in different sensitive groups but similar in node features. Second, to enhance model fairness and retain model quality, we develop a learnable neighbor sampling policy using reinforcement learning. To address the bias in node features and model parameters, FairSample is complemented by a regularization objective to optimize fairness.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 44 of its 76 references that are in the map. First posted on arXiv 26 Jan 2024.

Builds on

44 of 76 references.

References · 44

  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. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  7. 2019Simplifying Graph Convolutional Networkscited by 1,470
  8. 2020LightGCN: Simplifying and Powering Graph Convolution Network for Recommendationcited by 1,134
  9. 2018Deep Graph Infomaxcited by 1,101
  10. 2020Simple and Deep Graph Convolutional Networkscited by 857
  11. 2017Counterfactual Fairnesscited by 802
  12. 2014Certifying and removing disparate impactcited by 715
32 more
  1. 2018A Reductions Approach to Fair Classificationcited by 585
  2. 2018FastGCN: Fast Learning with Graph Convolutional Networks via Importance Samplingcited by 583
  3. 2020Graph Contrastive Learning with Adaptive Augmentationcited by 519
  4. 2020Graph Neural Networks in Recommender Systems: A Surveycited by 493
  5. 2020Towards Deeper Graph Neural Networkscited by 296
  6. 2019Label Propagation for Deep Semi-supervised Learningcited by 287
  7. 2018Empirical Risk Minimization under Fairness Constraintscited by 226
  8. 2018An Introduction to Deep Reinforcement Learningcited by 201
  9. 2020Data Augmentation for Graph Neural Networkscited by 200
  10. 2018Adaptive Sampling Towards Fast Graph Representation Learningcited by 180
  11. 2020Scaling Graph Neural Networks with Approximate PageRankcited by 174
  12. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  13. 2019Inherent Tradeoffs in Learning Fair Representationscited by 144
  14. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  15. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  16. 2020Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approachcited by 119
  17. 2020Disentangled Graph Collaborative Filteringcited by 118
  18. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  19. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  20. 2019Putting Fairness Principles into Practice: Challenges, Metrics, and Improvementscited by 70
  21. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  22. 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
  23. 2020Minimal Variance Sampling with Provable Guarantees for Fast Training of Graph Neural Networkscited by 54
  24. 2018FNNC: Achieving Fairness through Neural Networkscited by 43
  25. 2020All of the Fairness for Edge Prediction with Optimal Transportcited by 36
  26. 2020Bandit Samplers for Training Graph Neural Networkscited by 30
  27. 2022Fair Node Representation Learning via Adaptive Data Augmentationcited by 27
  28. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27
  29. 2021Training Fair Models in Federated Learning without Data Privacy Infringementcited by 26
  30. 2018Enhancing the Accuracy and Fairness of Human Decision Makingcited by 13
  31. 2022Fair Data Representation for Machine Learning at the Pareto Frontiercited by 12
  32. 2019The Pupil Has Become the Master: Teacher-Student Model-Based Word Embedding Distillation with Ensemble Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 2.

8 papers.

  1. 2024FairGT: A Fairness-aware Graph Transformercited by 29
  2. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2
  3. 2025CausalPre: Scalable and Effective Data Pre-Processing for Causal Fairnesscited by 2
  4. 2025FairGSE: Fairness-Aware Graph Neural Network without High False Positive Ratescited by 2
  5. 2024Bridging the Fairness Divide: Achieving Group and Individual Fairness in Graph Neural Networkscited by 1
  6. 2026Efficient Edge Rewiring Strategies for Enhancing PageRank Fairnesscited by 1
  7. 2024Physics-Guided Fair Graph Sampling for Water Temperature Prediction in River Networkscited by 0
  8. 2026Fairness-Aware Network Embeddings: Methods, Applications, and Challengescited by 0