mlsanityData to 7 Oct 2026

A Survey on Fairness for Machine Learning on Graphs

arXiv 2205.05396 ↗First posted 11 May 2022cs.LGcited by 20

Not on the map. Why?

Abstract (arXiv)

Nowadays, the analysis of complex phenomena modeled by graphs plays a crucial role in many real-world application domains where decisions can have a strong societal impact. However, numerous studies and papers have recently revealed that machine learning models could lead to potential disparate treatment between individuals and unfair outcomes. In that context, algorithmic contributions for graph mining are not spared by the problem of fairness and present some specific challenges related to the intrinsic nature of graphs: (1) graph data is non-IID, and this assumption may invalidate many existing studies in fair machine learning, (2) suited metric definitions to assess the different types of fairness with relational data and (3) algorithmic challenge on the difficulty of finding a good trade-off between model accuracy and fairness. This survey is the first one dedicated to fairness for relational data. It aims to present a comprehensive review of state-of-the-art techniques in fairness on graph mining and identify the open challenges and future trends. In particular, we start by presenting several sensible application domains and the associated graph mining tasks with a focus on edge prediction and node classification in the sequel. We also recall the different metrics proposed to evaluate potential bias at different levels of the graph mining process; then we provide a comprehensive overview of recent contributions in the domain of fair machine learning for graphs, that we classify into pre-processing, in-processing and post-processing models. We also propose to describe existing graph data, synthetic and real-world benchmarks. Finally, we present in detail five potential promising directions to advance research in studying algorithmic fairness on graphs.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 50 of its 101 references that are in the map. First posted on arXiv 11 May 2022.

Builds on

50 of 101 references.

References · 50

  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. 2013Auto-Encoding Variational Bayescited by 3,980
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  7. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  8. 2014DeepWalk: Online Learning of Social Representationscited by 1,543
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  11. 2017Counterfactual Fairnesscited by 802
  12. 2015LINE: Large-scale Information Network Embeddingcited by 582
38 more
  1. 2019Multi-scale Attributed Node Embeddingcited by 543
  2. 2020Fairness in Machine Learning: A Surveycited by 369
  3. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  4. 2015The Variational Fair Autoencodercited by 223
  5. 2019Flexibly Fair Representation Learning by Disentanglementcited by 196
  6. 2015Censoring Representations with an Adversarycited by 191
  7. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  8. 2021A survey on datasets for fairness-aware machine learningcited by 157
  9. 2018Classification with Fairness Constraints: A Meta-Algorithm with Provable Guaranteescited by 146
  10. 2017Fair Inference On Outcomescited by 143
  11. 2021Graph Learning: A Surveycited by 140
  12. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  13. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  14. 2019Fairness in Deep Learning: A Computational Perspectivecited by 123
  15. 2020Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Modelscited by 116
  16. 2018Optimization with Non-Differentiable Constraints with Applications to Fairness, Recall, Churn, and Other Goalscited by 103
  17. 2022Fairness in Graph Mining: A Surveycited by 76
  18. 2019Guarantees for Spectral Clustering with Fairness Constraintscited by 72
  19. 2019Putting Fairness Principles into Practice: Challenges, Metrics, and Improvementscited by 70
  20. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  21. 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
  22. 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
  23. 2021Fairness in Rankings and Recommendations: An Overviewcited by 62
  24. 2021On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Featurescited by 62
  25. 2018Fairness Through Computationally-Bounded Awarenesscited by 55
  26. 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
  27. 2020All of the Fairness for Edge Prediction with Optimal Transportcited by 36
  28. 2021CrossWalk: Fairness-enhanced Node Representation Learningcited by 34
  29. 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
  30. 2018Taking Advantage of Multitask Learning for Fair Classificationcited by 24
  31. 2019Group-Fairness in Influence Maximizationcited by 21
  32. 2020Exploring Algorithmic Fairness in Robust Graph Covering Problemscited by 19
  33. 2021The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizercited by 17
  34. 2018Conditional Network Embeddingscited by 15
  35. 2020Adversarial Graph Embeddings for Fair Influence Maximization over Social Networkscited by 15
  36. 2022FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modificationcited by 15
  37. 2020Fair Influence Maximization: A Welfare Optimization Approachcited by 12
  38. 2019MONET: Debiasing Graph Embeddings via the Metadata-Orthogonal Training Unitcited by 11

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 8; 2024: 3; 2025: 5; 2026: 4.

20 papers.

Sort:

By area:

  1. 2023Fairness-Aware Graph Neural Networks: A Surveycited by 22
  2. 2023(Un)fair devices: Moving beyond AI accuracy in personal sensingcited by 6
  3. 2023Deceptive Fairness Attacks on Graphs via Meta Learningcited by 6
  4. 2024FairWire: Fair Graph Generationcited by 6
  5. 2023Holistic Survey of Privacy and Fairness in Machine Learningcited by 4
  6. 2023Marginal Nodes Matter: Towards Structure Fairness in Graphscited by 2
  7. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2
  8. 2023CAFIN: Centrality Aware Fairness inducing IN-processing for Unsupervised Representation Learning on Graphscited by 1
  9. 2023Migrate Demographic Group For Fair GNNscited by 0
  10. 2023Explainable Graph Neural Architecture Search via Monte-Carlo Tree Search (Full version)cited by 0
  11. 2024Unbiased GNN Learning via Fairness-Aware Subgraph Diffusioncited by 0
  12. 2025Unlearning Algorithmic Biases over Graphscited by 0
8 more
  1. 2025FAROS: Fair Graph Generation via Attribute Switching Mechanismscited by 0
  2. 2025FnRGNN: Distribution-aware Fairness in Graph Neural Networkcited by 0
  3. 2025DynBERG: Dynamic BERT-based Graph neural network for financial fraud detectioncited by 0
  4. 2025FairExpand: Individual Fairness on Graphs with Partial Similarity Informationcited by 0
  5. 2026A Boolean Function-Theoretic Framework for Expressivity in GNNs with Applications to Fair Graph Miningcited by 0
  6. 2026Mitigating topology biases in Graph Diffusion via Counterfactual Interventioncited by 0
  7. 2026k-hop Fairness: Addressing Disparities in Graph Link Prediction Beyond First-Order Neighborhoodscited by 0
  8. 2026Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Networkcited by 0