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

arXiv: https://arxiv.org/abs/2201.03681 · HTML: https://mlsanity.com/paper/2201.03681/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 11 of its 19 references that are in the map.
- First posted on arXiv 10 Jan 2022.

## Builds on (most cited first, 11 of 11)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [node2vec: Scalable Feature Learning for Networks](https://mlsanity.com/paper/1607.00653/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Predict then Propagate: Graph Neural Networks meet Personalized PageRank](https://mlsanity.com/paper/1810.05997/) (2018)
- [Counterfactual Fairness](https://mlsanity.com/paper/1703.06856/) (2017)
- [Adversarial Attacks on Neural Networks for Graph Data](https://mlsanity.com/paper/1805.07984/) (2018)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Towards a Unified Framework for Fair and Stable Graph Representation Learning](https://mlsanity.com/paper/2102.13186/) (2021)
- [From Parity to Preference-based Notions of Fairness in Classification](https://mlsanity.com/paper/1707.00010/) (2017)

## Built on by (most cited first, 15 of 15)

- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Towards Fair Graph Neural Networks via Graph Counterfactual](https://mlsanity.com/paper/2307.04937/) (2023)
- [Fairness-Aware Graph Neural Networks: A Survey](https://mlsanity.com/paper/2307.03929/) (2023)
- [Interpreting Unfairness in Graph Neural Networks via Training Node Attribution](https://mlsanity.com/paper/2211.14383/) (2022)
- [Graph Learning with Localized Neighborhood Fairness](https://mlsanity.com/paper/2212.12040/) (2022)
- [Drop Edges and Adapt: a Fairness Enforcing Fine-tuning for Graph Neural Networks](https://mlsanity.com/paper/2302.11479/) (2023)
- [A Benchmark for Fairness-Aware Graph Learning](https://mlsanity.com/paper/2407.12112/) (2024)
- [Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributes](https://mlsanity.com/paper/2412.09947/) (2024)
- [Structural Bias Beyond Homophily: A Study of Fairness in Link Prediction](https://mlsanity.com/paper/2602.11802/) (2026)
- [Graph Neural Network Surrogates of Fair Graph Filtering](https://mlsanity.com/paper/2303.08157/) (2023)
- [Are Your Reviewers Being Treated Equally? Discovering Subgroup Structures to Improve Fairness in Spam Detection](https://mlsanity.com/paper/2204.11164/) (2022)
- [FnRGNN: Distribution-aware Fairness in Graph Neural Network](https://mlsanity.com/paper/2510.19257/) (2025)
- [Towards Fair Graph Prompting: A Dual-Prompt Mechanism for Mitigating Attribute and Structural Bias](https://mlsanity.com/paper/2510.23469/) (2025)
- [Geometrical fairness in graph neural networks](https://mlsanity.com/paper/2606.17684/) (2026)
- [FairProp: Fair Node Representation Learning via Differentiable Propagation Layers](https://mlsanity.com/paper/2610.06484/) (2026)

## 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.