mlsanityData to 14 Oct 2026

SaGIF: Improving Individual Fairness in Graph Neural Networks via Similarity Encoding

arXiv 2506.18696 ↗First posted 23 Jun 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Individual fairness (IF) in graph neural networks (GNNs), which emphasizes the need for similar individuals should receive similar outcomes from GNNs, has been a critical issue. Despite its importance, research in this area has been largely unexplored in terms of (1) a clear understanding of what induces individual unfairness in GNNs and (2) a comprehensive consideration of identifying similar individuals. To bridge these gaps, we conduct a preliminary analysis to explore the underlying reason for individual unfairness and observe correlations between IF and similarity consistency, a concept introduced to evaluate the discrepancy in identifying similar individuals based on graph structure versus node features. Inspired by our observations, we introduce two metrics to assess individual similarity from two distinct perspectives: topology fusion and feature fusion. Building upon these metrics, we propose Similarity-aware GNNs for Individual Fairness, named SaGIF. The key insight behind SaGIF is the integration of individual similarities by independently learning similarity representations, leading to an improvement of IF in GNNs. Our experiments on several real-world datasets validate the effectiveness of our proposed metrics and SaGIF. Specifically, SaGIF consistently outperforms state-of-the-art IF methods while maintaining utility performance. Code is available at: https://github.com/ZzoomD/SaGIF.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 34 of its 49 references that are in the map. First posted on arXiv 23 Jun 2025.

Builds on

34 of 49 references.

References · 34

  1. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  2. 2017Inductive Representation Learning on Large Graphscited by 6,320
  3. 2016Equality of Opportunity in Supervised Learningcited by 2,007
  4. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,917
  5. 2019Simplifying Graph Convolutional Networkscited by 1,477
  6. 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
  7. 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
  8. 2017Counterfactual Fairnesscited by 804
  9. 2019Graph Neural Networks for Social Recommendationcited by 714
  10. 2020Benchmarking Graph Neural Networkscited by 680
  11. 2019Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networkscited by 541
  12. 2018Fairness Without Demographics in Repeated Loss Minimizationcited by 364
22 more
  1. 2018Learning Adversarially Fair and Transferable Representationscited by 353
  2. 2021Graph Neural Networks with Learnable Structural and Positional Representationscited by 333
  3. 2019Position-aware Graph Neural Networkscited by 203
  4. 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
  5. 2021GraphiT: Encoding Graph Structure in Transformerscited by 147
  6. 2021Towards a Unified Framework for Fair and Stable Graph Representation Learningcited by 128
  7. 2020Node Similarity Preserving Graph Convolutional Networkscited by 112
  8. 2020Unifying Graph Convolutional Neural Networks and Label Propagationcited by 98
  9. 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
  10. 2021Subgroup Generalization and Fairness of Graph Neural Networkscited by 69
  11. 2018iFair: Learning Individually Fair Data Representations for Algorithmic Decision Makingcited by 64
  12. 2019Operationalizing Individual Fairness with Pairwise Fair Representationscited by 64
  13. 2021Post-processing for Individual Fairnesscited by 61
  14. 2020Two Simple Ways to Learn Individual Fairness Metrics from Datacited by 54
  15. 2020Verifying Individual Fairness in Machine Learning Modelscited by 49
  16. 2021Fair Representation Learning for Heterogeneous Information Networkscited by 28
  17. 2022RawlsGCN: Towards Rawlsian Difference Principle on Graph Convolutional Networkcited by 27
  18. 2022Accurate Fairness: Improving Individual Fairness without Trading Accuracycited by 16
  19. 2023Learning for Counterfactual Fairness from Observational Datacited by 13
  20. 2023FAIRER: Fairness as Decision Rationale Alignmentcited by 12
  21. 2023GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hintcited by 6
  22. 2022Position-Aware Subgraph Neural Networks with Data-Efficient Learningcited by 3

Built on by

Not cited yet.