# Rethinking Fair Graph Neural Networks from Re-balancing

arXiv: https://arxiv.org/abs/2407.11624 · HTML: https://mlsanity.com/paper/2407.11624/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 35 of its 62 references that are in the map.
- First posted on arXiv 16 Jul 2024.

## Builds on (most cited first, 30 of 35)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Path-Specific Counterfactual Fairness](https://mlsanity.com/paper/1802.08139/) (2018)
- [Simple data balancing achieves competitive worst-group-accuracy](https://mlsanity.com/paper/2110.14503/) (2021)
- [Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information](https://mlsanity.com/paper/2009.01454/) (2020)
- [Data Decisions and Theoretical Implications when Adversarially Learning Fair Representations](https://mlsanity.com/paper/1707.00075/) (2017)
- [GraphSMOTE: Imbalanced Node Classification on Graphs with Graph Neural Networks](https://mlsanity.com/paper/2103.08826/) (2021)
- [Why Is My Classifier Discriminatory?](https://mlsanity.com/paper/1805.12002/) (2018)
- [Causal Attention for Interpretable and Generalizable Graph Classification](https://mlsanity.com/paper/2112.15089/) (2021)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs](https://mlsanity.com/paper/2402.11235/) (2024)
- [GAMENet: Graph Augmented MEmory Networks for Recommending Medication Combination](https://mlsanity.com/paper/1809.01852/) (2018)
- [Debiasing Graph Neural Networks via Learning Disentangled Causal Substructure](https://mlsanity.com/paper/2209.14107/) (2022)
- [Fairness in Graph Mining: A Survey](https://mlsanity.com/paper/2204.09888/) (2022)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Topology-Imbalance Learning for Semi-Supervised Node Classification](https://mlsanity.com/paper/2110.04099/) (2021)
- [Two Simple Ways to Learn Individual Fairness Metrics from Data](https://mlsanity.com/paper/2006.11439/) (2020)
- [GSLB: The Graph Structure Learning Benchmark](https://mlsanity.com/paper/2310.05174/) (2023)
- [Average Individual Fairness: Algorithms, Generalization and Experiments](https://mlsanity.com/paper/1905.10607/) (2019)
- [TAM: Topology-Aware Margin Loss for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2206.12917/) (2022)
- [FMP: Toward Fair Graph Message Passing against Topology Bias](https://mlsanity.com/paper/2202.04187/) (2022)
- [CrossWalk: Fairness-enhanced Node Representation Learning](https://mlsanity.com/paper/2105.02725/) (2021)
- [Bias Mimicking: A Simple Sampling Approach for Bias Mitigation](https://mlsanity.com/paper/2209.15605/) (2022)
- [Towards Fair Graph Neural Networks via Graph Counterfactual](https://mlsanity.com/paper/2307.04937/) (2023)
- [Uncovering Neural Scaling Laws in Molecular Representation Learning](https://mlsanity.com/paper/2309.15123/) (2023)
- [GraphSHA: Synthesizing Harder Samples for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2306.09612/) (2023)

## Built on by (most cited first, 11 of 11)

- [G-Refer: Graph Retrieval-Augmented Large Language Model for Explainable Recommendation](https://mlsanity.com/paper/2502.12586/) (2025)
- [GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning](https://mlsanity.com/paper/2410.13761/) (2024)
- [IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification](https://mlsanity.com/paper/2502.06280/) (2025)
- [FairGE: Fairness-Aware Graph Encoding in Incomplete Social Networks](https://mlsanity.com/paper/2601.09394/) (2026)
- [Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs](https://mlsanity.com/paper/2510.18473/) (2025)
- [Toward Fair Graph Neural Networks Via Dual-Teacher Knowledge Distillation](https://mlsanity.com/paper/2412.00382/) (2024)
- [Learning Fair Graph Representations with Multi-view Information Bottleneck](https://mlsanity.com/paper/2510.25096/) (2025)
- [Towards Fair Graph Representation Learning in Social Networks](https://mlsanity.com/paper/2410.11493/) (2024)
- [Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Information](https://mlsanity.com/paper/2512.03074/) (2025)
- [Homophily-aware Supervised Contrastive Counterfactual Augmented Fair Graph Neural Network](https://mlsanity.com/paper/2604.02342/) (2026)
- [Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics](https://mlsanity.com/paper/2607.14705/) (2026)

## Abstract (arXiv)

Driven by the powerful representation ability of Graph Neural Networks (GNNs), plentiful GNN models have been widely deployed in many real-world applications. Nevertheless, due to distribution disparities between different demographic groups, fairness in high-stake decision-making systems is receiving increasing attention. Although lots of recent works devoted to improving the fairness of GNNs and achieved considerable success, they all require significant architectural changes or additional loss functions requiring more hyper-parameter tuning. Surprisingly, we find that simple re-balancing methods can easily match or surpass existing fair GNN methods. We claim that the imbalance across different demographic groups is a significant source of unfairness, resulting in imbalanced contributions from each group to the parameters updating. However, these simple re-balancing methods have their own shortcomings during training. In this paper, we propose FairGB, Fair Graph Neural Network via re-Balancing, which mitigates the unfairness of GNNs by group balancing. Technically, FairGB consists of two modules: counterfactual node mixup and contribution alignment loss. Firstly, we select counterfactual pairs across inter-domain and inter-class, and interpolate the ego-networks to generate new samples. Guided by analysis, we can reveal the debiasing mechanism of our model by the causal view and prove that our strategy can make sensitive attributes statistically independent from target labels. Secondly, we reweigh the contribution of each group according to gradients. By combining these two modules, they can mutually promote each other. Experimental results on benchmark datasets show that our method can achieve state-of-the-art results concerning both utility and fairness metrics. Code is available at https://github.com/ZhixunLEE/FairGB.