mlsanityData to 7 Oct 2026

Promoting Fairness in Link Prediction with Graph Enhancement

arXiv 2409.08658 ↗First posted 13 Sep 2024cs.LGcited by 6

Not on the map. Why?

Abstract (arXiv)

Link prediction is a crucial task in network analysis, but it has been shown to be prone to biased predictions, particularly when links are unfairly predicted between nodes from different sensitive groups. In this paper, we study the fair link prediction problem, which aims to ensure that the predicted link probability is independent of the sensitive attributes of the connected nodes. Existing methods typically incorporate debiasing techniques within graph embeddings to mitigate this issue. However, training on large real-world graphs is already challenging, and adding fairness constraints can further complicate the process. To overcome this challenge, we propose FairLink, a method that learns a fairness-enhanced graph to bypass the need for debiasing during the link predictor's training. FairLink maintains link prediction accuracy by ensuring that the enhanced graph follows a training trajectory similar to that of the original input graph. Meanwhile, it enhances fairness by minimizing the absolute difference in link probabilities between node pairs within the same sensitive group and those between node pairs from different sensitive groups. Our extensive experiments on multiple large-scale graphs demonstrate that FairLink not only promotes fairness but also often achieves link prediction accuracy comparable to baseline methods. Most importantly, the enhanced graph exhibits strong generalizability across different GNN architectures.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 44 of its 70 references that are in the map. First posted on arXiv 13 Sep 2024.

Builds on

44 of 70 references.

References · 44

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  6. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  7. 2016Variational Graph Auto-Encoderscited by 1,373
  8. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 970
  9. 2016Complex Embeddings for Simple Link Predictioncited by 897
  10. 2017Counterfactual Fairnesscited by 802
  11. 2014Certifying and removing disparate impactcited by 715
  12. 2020Dataset Condensation with Gradient Matchingcited by 510
32 more
  1. 2016Fairness Beyond Disparate Treatment & Disparate Impact: Learning Classification without Disparate Mistreatmentcited by 368
  2. 2021Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Predictioncited by 273
  3. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  4. 2021Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillationcited by 151
  5. 2021Graph Condensation for Graph Neural Networkscited by 150
  6. 2020Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learningcited by 148
  7. 2017A Survey on Network Embeddingcited by 142
  8. 2019Compositional Fairness Constraints for Graph Embeddingscited by 126
  9. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  10. 2021Fair Mixup: Fairness via Interpolationcited by 109
  11. 2022Condensing Graphs via One-Step Gradient Matchingcited by 100
  12. 2022Equivariant and Stable Positional Encoding for More Powerful Graph Neural Networkscited by 94
  13. 2022Fairness in Graph Mining: A Surveycited by 76
  14. 2021Graph-MLP: Node Classification without Message Passing in Graphcited by 73
  15. 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
  16. 2016Satisfying Real-world Goals with Dataset Constraintscited by 68
  17. 2022Empowering Graph Representation Learning with Test-Time Graph Transformationcited by 66
  18. 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
  19. 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
  20. 2023Data-centric AI: Perspectives and Challengescited by 43
  21. 2022MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initializationcited by 31
  22. 2022TF-GNN: Graph Neural Networks in TensorFlowcited by 21
  23. 2022FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modificationcited by 15
  24. 2022Contrastive Knowledge Graph Error Detectioncited by 11
  25. 2022Explaining Dynamic Graph Neural Networks via Relevance Back-propagationcited by 8
  26. 2017Homophily and minority size explain perception biases in social networkscited by 7
  27. 2024Addressing Shortcomings in Fair Graph Learning Datasets: Towards a New Benchmarkcited by 7
  28. 2024TinyGraph: Joint Feature and Node Condensation for Graph Neural Networkscited by 5
  29. 2019Mathematical model of gender bias and homophily in professional hierarchiescited by 4
  30. 2020Benchmarking Network Embedding Models for Link Prediction: Are We Making Progress?cited by 4
  31. 2019Network Representation Learning: Consolidation and Renewed Bearingcited by 3
  32. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2025: 6.

6 papers.

  1. 2025LUNE: Efficient LLM Unlearning via LoRA Fine-Tuning with Negative Examplescited by 8
  2. 2025Enabling Group Fairness in Graph Unlearning via Bi-level Debiasingcited by 3
  3. 2025Recover-to-Forget: Gradient Reconstruction from LoRA for Efficient LLM Unlearningcited by 1
  4. 2025Information Loss and Disparate Effects in Network Embeddingscited by 0
  5. 2025Estimating Fair Graphs from Graph-Stationary Datacited by 0
  6. 2025Mitigating Bias in Graph Hyperdimensional Computingcited by 0