mlsanityData to 7 Oct 2026

FMP: Toward Fair Graph Message Passing against Topology Bias

arXiv 2202.04187 ↗First posted 8 Feb 2022cs.LGcited by 35

Not on the map. Why?

Abstract (arXiv)

Despite recent advances in achieving fair representations and predictions through regularization, adversarial debiasing, and contrastive learning in graph neural networks (GNNs), the working mechanism (i.e., message passing) behind GNNs inducing unfairness issue remains unknown. In this work, we theoretically and experimentally demonstrate that representative aggregation in message-passing schemes accumulates bias in node representation due to topology bias induced by graph topology. Thus, a textsfFair textsfMessage textsfPassing (FMP) scheme is proposed to aggregate useful information from neighbors but minimize the effect of topology bias in a unified framework considering graph smoothness and fairness objectives. The proposed FMP is effective, transparent, and compatible with back-propagation training. An acceleration approach on gradient calculation is also adopted to improve algorithm efficiency. Experiments on node classification tasks demonstrate that the proposed FMP outperforms the state-of-the-art baselines in effectively and efficiently mitigating bias on three real-world datasets.

Key facts. Cited by 35 papers in the map (data through 7 Oct 2026). Builds on 36 of its 47 references that are in the map. First posted on arXiv 8 Feb 2022.

Builds on

36 of 47 references.

References · 36

  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. 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,085
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2019Simplifying Graph Convolutional Networkscited by 1,470
  7. 2018Graph Convolutional Neural Networks for Web-Scale Recommender Systemscited by 1,133
  8. 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,097
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  10. 2014Certifying and removing disparate impactcited by 715
  11. 2018Mitigating Unwanted Biases with Adversarial Learningcited by 663
  12. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
24 more
  1. 2016Geometric deep learning on graphs and manifolds using mixture model CNNscited by 468
  2. 2019PairNorm: Tackling Oversmoothing in GNNscited by 297
  3. 2015Deep Convolutional Networks on Graph-Structured Datacited by 246
  4. 2015The Variational Fair Autoencodercited by 223
  5. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  6. 2021Is Homophily a Necessity for Graph Neural Networks?cited by 182
  7. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  8. 2017Data Decisions and Theoretical Implications when Adversarially Learning Fair Representationscited by 165
  9. 2021Interpreting and Unifying Graph Neural Networks with An Optimization Frameworkcited by 131
  10. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  11. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  12. 2018Large-Scale Learnable Graph Convolutional Networkscited by 113
  13. 2020A Unified View on Graph Neural Networks as Graph Signal Denoisingcited by 110
  14. 2021Fair Mixup: Fairness via Interpolationcited by 109
  15. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  16. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  17. 2021Elastic Graph Neural Networkscited by 67
  18. 2021Fairness via Representation Neutralizationcited by 63
  19. 2016Learning to Pivot with Adversarial Networkscited by 55
  20. 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
  21. 2020SenSeI: Sensitive Set Invariance for Enforcing Individual Fairnesscited by 37
  22. 2020All of the Fairness for Edge Prediction with Optimal Transportcited by 36
  23. 2021Fairness-Aware Node Representation Learningcited by 14
  24. 2016Do the Young Live in a "Smaller World" Than the Old? Age-Specific Degrees of Separation in Human Communicationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 19; 2024: 7; 2025: 2; 2026: 2.

35 papers.

Sort:

By area:

  1. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  2. 2022Fairness in Graph Mining: A Surveycited by 76
  3. 2023Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?cited by 41
  4. 2023Towards Fair Graph Neural Networks via Graph Counterfactualcited by 23
  5. 2023Counterfactual Learning on Graphs: A Surveycited by 22
  6. 2023Fairness-Aware Graph Neural Networks: A Surveycited by 22
  7. 2024FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralizationcited by 20
  8. 2023LazyGNN: Large-Scale Graph Neural Networks via Lazy Propagationcited by 16
  9. 2023The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillationcited by 16
  10. 2022RSC: Accelerating Graph Neural Networks Training via Randomized Sparse Computationscited by 12
  11. 2023Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approachcited by 12
  12. 2023BeMap: Balanced Message Passing for Fair Graph Neural Networkcited by 11
23 more
  1. 2024Rethinking Fair Graph Neural Networks from Re-balancingcited by 11
  2. 2022Graph Learning with Localized Neighborhood Fairnesscited by 10
  3. 2023Collaborative Graph Neural Networks for Attributed Network Embeddingcited by 8
  4. 2023Fairness-aware Message Passing for Graph Neural Networkscited by 7
  5. 2023Retiring DeltaDP: New Distribution-Level Metrics for Demographic Paritycited by 4
  6. 2023Adversarial Attacks on Fairness of Graph Neural Networkscited by 4
  7. 2023Editable Graph Neural Network for Node Classificationscited by 3
  8. 2023Towards Label Position Bias in Graph Neural Networkscited by 3
  9. 2024On Explaining Unfairness: An Overviewcited by 3
  10. 2025Enabling Group Fairness in Graph Unlearning via Bi-level Debiasingcited by 3
  11. 2022Towards Understanding Graph Neural Networks: An Algorithm Unrolling Perspectivecited by 2
  12. 2023DiscoverPath: A Knowledge Refinement and Retrieval System for Interdisciplinarity on Biomedical Researchcited by 2
  13. 2023Equipping Federated Graph Neural Networks with Structure-aware Group Fairnesscited by 2
  14. 2023Marginal Nodes Matter: Towards Structure Fairness in Graphscited by 2
  15. 2024MAPPING: Debiasing Graph Neural Networks for Fair Node Classification with Limited Sensitive Information Leakagecited by 2
  16. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2
  17. 2024Mitigating Degree Bias in Signed Graph Neural Networkscited by 2
  18. 2022ASGNN: Graph Neural Networks with Adaptive Structurecited by 1
  19. 2024Gradient Rewiring for Editable Graph Neural Network Trainingcited by 1
  20. 2023Migrate Demographic Group For Fair GNNscited by 0
  21. 2025Estimating Fair Graphs from Graph-Stationary Datacited by 0
  22. 2026A Boolean Function-Theoretic Framework for Expressivity in GNNs with Applications to Fair Graph Miningcited by 0
  23. 2026Subgraph Filtering for Fair Graph Neural Networkscited by 0