Structural Bias Beyond Homophily: A Study of Fairness in Link Prediction
Not on the map. Why?
Abstract (arXiv)
Graph link prediction (LP) plays a critical role in socially impactful applications such as job recommendation and friendship formation, making fairness a critical concern in this task. While many fairness-aware methods manipulate graph structures to mitigate prediction disparities, the topological biases inherent to social graphs remain poorly understood and are consistently conflated with homophily alone. In this work, we study the relationship between structural biases and fairness outcomes in LP. To this end, we formalize a taxonomy of topological bias measures and introduce a graph generation method producing a diverse corpus of synthetic graphs with controlled structural properties. Using this corpus, we show empirically that fairness outcomes are strongly correlated with graph topology, and that current fairness-aware methods remain sensitive to structural biases beyond homophily. These findings highlight the need for structurally grounded evaluations in fair graph learning.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 22 of its 39 references that are in the map. First posted on arXiv 12 Feb 2026.
Builds on
22 of 39 references.
References · 22
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
- 2016node2vec: Scalable Feature Learning for Networkscited by 1,913
- 2018Pitfalls of Graph Neural Network Evaluationcited by 994
- 2020Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Informationcited by 168
- 2018Contextual Stochastic Block Modelscited by 134
- 2021EDITS: Modeling and Mitigating Data Bias for Graph Neural Networkscited by 92
- 2022A Survey on Deep Graph Generation: Methods and Applicationscited by 69
- 2023Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarkingcited by 69
- 2021FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learningcited by 68
- 2020DeBayes: a Bayesian Method for Debiasing Network Embeddingscited by 55
- 2020All of the Fairness for Edge Prediction with Optimal Transportcited by 36
- 2021CrossWalk: Fairness-enhanced Node Representation Learningcited by 34
10 more
- 2021Unbiased Graph Embedding with Biased Graph Observationscited by 28
- 2022Beyond Real-world Benchmark Datasets: An Empirical Study of Node Classification with GNNscited by 23
- 2022FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editingcited by 14
- 2023FairGen: Towards Fair Graph Generationcited by 12
- 2021GenCAT: Generating Attributed Graphs with Controlled Relationships between Classes, Attributes, and Topologycited by 10
- 2022Graph Learning with Localized Neighborhood Fairnesscited by 10
- 2024What Is Missing In Homophily? Disentangling Graph Homophily For Graph Neural Networkscited by 9
- 2023Networked Inequality: Preferential Attachment Bias in Graph Neural Network Link Predictioncited by 8
- 2023Structural Group Unfairness: Measurement and Mitigation by means of the Effective Resistancecited by 4
- 2023A Topology-aware Analysis of Graph Collaborative Filteringcited by 2
Built on by
Citing papers per year: 2026: 2.
2 papers.