mlsanityData to 7 Oct 2026

DeBayes: a Bayesian Method for Debiasing Network Embeddings

arXiv 2002.11442 ↗First posted 26 Feb 2020cs.LG stat.MLcited by 55

Not on the map. Why?

Abstract (arXiv)

As machine learning algorithms are increasingly deployed for high-impact automated decision making, ethical and increasingly also legal standards demand that they treat all individuals fairly, without discrimination based on their age, gender, race or other sensitive traits. In recent years much progress has been made on ensuring fairness and reducing bias in standard machine learning settings. Yet, for network embedding, with applications in vulnerable domains ranging from social network analysis to recommender systems, current options remain limited both in number and performance. We thus propose DeBayes: a conceptually elegant Bayesian method that is capable of learning debiased embeddings by using a biased prior. Our experiments show that these representations can then be used to perform link prediction that is significantly more fair in terms of popular metrics such as demographic parity and equalized opportunity.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 5; 2022: 16; 2023: 15; 2024: 6; 2025: 7; 2026: 6.

55 papers.

Sort:

By area:

  1. 2022A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainabilitycited by 118
  2. 2022Fairness in Graph Mining: A Surveycited by 76
  3. 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
  4. 2022Learning Fair Node Representations with Graph Counterfactual Fairnesscited by 58
  5. 2022Representation Bias in Data: A Survey on Identification and Resolution Techniquescited by 37
  6. 2022FMP: Toward Fair Graph Message Passing against Topology Biascited by 35
  7. 2021CrossWalk: Fairness-enhanced Node Representation Learningcited by 34
  8. 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
  9. 2023On Generalized Degree Fairness in Graph Neural Networkscited by 28
  10. 2022Fair Node Representation Learning via Adaptive Data Augmentationcited by 27
  11. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27
  12. 2023Fairness-Aware Graph Neural Networks: A Surveycited by 22
38 more
  1. 2022Fairness Amidst Non-IID Graph Data: A Literature Reviewcited by 20
  2. 2022A Survey on Fairness for Machine Learning on Graphscited by 20
  3. 2021The KL-Divergence between a Graph Model and its Fair I-Projection as a Fairness Regularizercited by 17
  4. 2023A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directionscited by 15
  5. 2023FairGAT: Fairness-aware Graph Attention Networkscited by 12
  6. 2023FairGen: Towards Fair Graph Generationcited by 12
  7. 2023Chasing Fairness in Graphs: A GNN Architecture Perspectivecited by 12
  8. 2024FUGNN: Harmonizing Fairness and Utility in Graph Neural Networkscited by 11
  9. 2022Graph Learning with Localized Neighborhood Fairnesscited by 10
  10. 2024Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behaviorcited by 9
  11. 2021EqGNN: Equalized Node Opportunity in Graphscited by 7
  12. 2023Toward Operationalizing Pipeline-aware ML Fairness: A Research Agenda for Developing Practical Guidelines and Toolscited by 7
  13. 2022Obtaining Dyadic Fairness by Optimal Transportcited by 6
  14. 2023GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hintcited by 6
  15. 2024FairWire: Fair Graph Generationcited by 6
  16. 2024Promoting Fairness in Link Prediction with Graph Enhancementcited by 6
  17. 2022FairNorm: Fair and Fast Graph Neural Network Trainingcited by 4
  18. 2022Impact Of Missing Data Imputation On The Fairness And Accuracy Of Graph Node Classifierscited by 3
  19. 2023Towards Label Position Bias in Graph Neural Networkscited by 3
  20. 2023Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networkscited by 2
  21. 2023Consumer-side Fairness in Recommender Systems: A Systematic Survey of Methods and Evaluationcited by 2
  22. 2023Fairness-aware Optimal Graph Filter Designcited by 2
  23. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2
  24. 2026Structural Bias Beyond Homophily: A Study of Fairness in Link Predictioncited by 2
  25. 2022Lessons Learned: Defending Against Property Inference Attackscited by 1
  26. 2022Data Augmentation for Graph Data: Recent Advancementscited by 1
  27. 2024Fair Graph Neural Network with Supervised Contrastive Regularizationcited by 1
  28. 2022Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detectioncited by 0
  29. 2023Providing Previously Unseen Users Fair Recommendations Using Variational Autoencoderscited by 0
  30. 2023Promoting Fairness in GNNs: A Characterization of Stabilitycited by 0
  31. 2023Fair Graph Machine Learning under Adversarial Missingness Processescited by 0
  32. 2025Causally Fair Node Classification on Non-IID Graph Datacited by 0
  33. 2025Unlearning Algorithmic Biases over Graphscited by 0
  34. 2025Let's Grow an Unbiased Community: Guiding the Fairness of Graphs via New Linkscited by 0
  35. 2025Information Loss and Disparate Effects in Network Embeddingscited by 0
  36. 2025Estimating Fair Graphs from Graph-Stationary Datacited by 0
  37. 2025FnRGNN: Distribution-aware Fairness in Graph Neural Networkcited by 0
  38. 2025Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Informationcited by 0

50 most cited of 55 All 55 (JSON)