mlsanityData to 7 Oct 2026

FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing

arXiv 2201.03681 ↗First posted 10 Jan 2022cs.LGcited by 14

Not on the map. Why?

Abstract (arXiv)

Graph Neural Networks (GNNs) have proven to excel in predictive modeling tasks where the underlying data is a graph. However, as GNNs are extensively used in human-centered applications, the issue of fairness has arisen. While edge deletion is a common method used to promote fairness in GNNs, it fails to consider when data is inherently missing fair connections. In this work we consider the unexplored method of edge addition, accompanied by deletion, to promote fairness. We propose two model-agnostic algorithms to perform edge editing: a brute force approach and a continuous approximation approach, FairEdit. FairEdit performs efficient edge editing by leveraging gradient information of a fairness loss to find edges that improve fairness. We find that FairEdit outperforms standard training for many data sets and GNN methods, while performing comparably to many state-of-the-art methods, demonstrating FairEdit's ability to improve fairness across many domains and models.

Key facts. Cited by 14 papers in the map (data through 7 Oct 2026). Builds on 11 of its 19 references that are in the map. First posted on arXiv 10 Jan 2022.

Builds on

11 of 19 references.

References · 11

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  2. 2017Inductive Representation Learning on Large Graphscited by 6,284
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,000
  4. 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
  5. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 987
  7. 2017Counterfactual Fairnesscited by 802
  8. 2018Adversarial Attacks on Neural Networks for Graph Datacited by 395
  9. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  10. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  11. 2017From Parity to Preference-based Notions of Fairness in Classificationcited by 60

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 4; 2023: 4; 2024: 2; 2025: 2; 2026: 2.

14 papers.

Sort:

  1. 2022Fairness in Graph Mining: A Surveycited by 76
  2. 2023Towards Fair Graph Neural Networks via Graph Counterfactualcited by 23
  3. 2023Fairness-Aware Graph Neural Networks: A Surveycited by 22
  4. 2022Interpreting Unfairness in Graph Neural Networks via Training Node Attributioncited by 18
  5. 2022Graph Learning with Localized Neighborhood Fairnesscited by 10
  6. 2023Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networkscited by 2
  7. 2024A Benchmark for Fairness-Aware Graph Learningcited by 2
  8. 2024Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributescited by 2
  9. 2026Structural Bias Beyond Homophily: A Study of Fairness in Link Predictioncited by 2
  10. 2023Graph Neural Network Surrogates of Fair Graph Filteringcited by 1
  11. 2022Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detectioncited by 0
  12. 2025FnRGNN: Distribution-aware Fairness in Graph Neural Networkcited by 0
2 more
  1. 2025Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Biascited by 0
  2. 2026Geometrical fairness in graph neural networkscited by 0