# Towards Fair Graph Neural Networks via Graph Counterfactual without Sensitive Attributes

arXiv: https://arxiv.org/abs/2412.09947 · HTML: https://mlsanity.com/paper/2412.09947/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 46 references that are in the map.
- First posted on arXiv 13 Dec 2024.

## Builds on (most cited first, 26 of 26)

- [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)
- [A Comprehensive Survey on Graph Neural Networks](https://mlsanity.com/paper/1901.00596/) (2019)
- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Spectral Networks and Locally Connected Networks on Graphs](https://mlsanity.com/paper/1312.6203/) (2013)
- [Fairness without Demographics through Adversarially Reweighted Learning](https://mlsanity.com/paper/2006.13114/) (2020)
- [Graph Clustering with Graph Neural Networks](https://mlsanity.com/paper/2006.16904/) (2020)
- [EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks](https://mlsanity.com/paper/2108.05233/) (2021)
- [Improving Fairness in Graph Neural Networks via Mitigating Sensitive Attribute Leakage](https://mlsanity.com/paper/2206.03426/) (2022)
- [Learning Fair Node Representations with Graph Counterfactual Fairness](https://mlsanity.com/paper/2201.03662/) (2022)
- [Search to aggregate neighborhood for graph neural network](https://mlsanity.com/paper/2104.06608/) (2021)
- [Towards Fair Classifiers Without Sensitive Attributes: Exploring Biases in Related Features](https://mlsanity.com/paper/2104.14537/) (2021)
- [Multi-level Graph Convolutional Networks for Cross-platform Anchor Link Prediction](https://mlsanity.com/paper/2006.01963/) (2020)
- [A Survey on Graph Counterfactual Explanations: Definitions, Methods, Evaluation, and Research Challenges](https://mlsanity.com/paper/2210.12089/) (2022)
- [Towards Fair Graph Neural Networks via Graph Counterfactual](https://mlsanity.com/paper/2307.04937/) (2023)
- [FairSIN: Achieving Fairness in Graph Neural Networks through Sensitive Information Neutralization](https://mlsanity.com/paper/2403.12474/) (2024)
- [HyGNN: Drug-Drug Interaction Prediction via Hypergraph Neural Network](https://mlsanity.com/paper/2206.12747/) (2022)
- [The Devil is in the Data: Learning Fair Graph Neural Networks via Partial Knowledge Distillation](https://mlsanity.com/paper/2311.17373/) (2023)
- [FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing](https://mlsanity.com/paper/2201.03681/) (2022)
- [Search to Fine-tune Pre-trained Graph Neural Networks for Graph-level Tasks](https://mlsanity.com/paper/2308.06960/) (2023)
- [GraphRARE: Reinforcement Learning Enhanced Graph Neural Network with Relative Entropy](https://mlsanity.com/paper/2312.09708/) (2023)
- [Local-Global History-aware Contrastive Learning for Temporal Knowledge Graph Reasoning](https://mlsanity.com/paper/2312.01601/) (2023)
- [Addressing Shortcomings in Fair Graph Learning Datasets: Towards a New Benchmark](https://mlsanity.com/paper/2403.06017/) (2024)
- [Learning Fair Models without Sensitive Attributes: A Generative Approach](https://mlsanity.com/paper/2203.16413/) (2022)
- [Scalable Graph Convolutional Network Training on Distributed-Memory Systems](https://mlsanity.com/paper/2212.05009/) (2022)

## Built on by (most cited first, 2 of 2)

- [Grad2Fair: A Gradient-driven Approach for Graph Fairness without Demographics](https://mlsanity.com/paper/2607.14705/) (2026)
- [Fairness-Aware Network Embeddings: Methods, Applications, and Challenges](https://mlsanity.com/paper/2608.19381/) (2026)

## Abstract (arXiv)

Graph-structured data is ubiquitous in today's connected world, driving extensive research in graph analysis. Graph Neural Networks (GNNs) have shown great success in this field, leading to growing interest in developing fair GNNs for critical applications. However, most existing fair GNNs focus on statistical fairness notions, which may be insufficient when dealing with statistical anomalies. Hence, motivated by causal theory, there has been growing attention to mitigating root causes of unfairness utilizing graph counterfactuals. Unfortunately, existing methods for generating graph counterfactuals invariably require the sensitive attribute. Nevertheless, in many real-world applications, it is usually infeasible to obtain sensitive attributes due to privacy or legal issues, which challenge existing methods. In this paper, we propose a framework named Fairwos (improving Fairness without sensitive attributes). In particular, we first propose a mechanism to generate pseudo-sensitive attributes to remedy the problem of missing sensitive attributes, and then design a strategy for finding graph counterfactuals from the real dataset. To train fair GNNs, we propose a method to ensure that the embeddings from the original data are consistent with those from the graph counterfactuals, and dynamically adjust the weight of each pseudo-sensitive attribute to balance its contribution to fairness and utility. Furthermore, we theoretically demonstrate that minimizing the relation between these pseudo-sensitive attributes and the prediction can enable the fairness of GNNs. Experimental results on six real-world datasets show that our approach outperforms state-of-the-art methods in balancing utility and fairness.