Towards Fair Graph Neural Networks via Graph Counterfactual

Abstract

Graph neural networks have shown great ability in representation (GNNs) learning on graphs, facilitating various tasks. Despite their great performance in modeling graphs, recent works show that GNNs tend to inherit and amplify the bias from training data, causing concerns of the adoption of GNNs in high-stake scenarios. Hence, many efforts have been taken for fairness-aware GNNs. However, most existing fair GNNs learn fair node representations by adopting statistical fairness notions, which may fail to alleviate bias in the presence of statistical anomalies. Motivated by causal theory, there are several attempts utilizing graph counterfactual fairness to mitigate root causes of unfairness. However, these methods suffer from non-realistic counterfactuals obtained by perturbation or generation. In this paper, we take a causal view on fair graph learning problem. Guided by the casual analysis, we propose a novel framework CAF, which can select counterfactuals from training data to avoid non-realistic counterfactuals and adopt selected counterfactuals to learn fair node representations for node classification task. Extensive experiments on synthetic and real-world datasets show the effectiveness of CAF. Our code is available at https://github.com/TimeLovercc/CAF-GNN.

References in corpus (14)

• A Comprehensive Survey on Graph Neural Networks
• Equality of Opportunity in Supervised Learning
• Counterfactual Fairness
• Causal Attention for Interpretable and Generalizable Graph Classification
• EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks
• Explainability in Graph Neural Networks: A Taxonomic Survey
• Learning Fair Node Representations with Graph Counterfactual Fairness
• Survey on Causal-based Machine Learning Fairness Notions
• HousE: Knowledge Graph Embedding with Householder Parameterization
• FMP: Toward Fair Graph Message Passing against Topology Bias
• Learning from Counterfactual Links for Link Prediction
• Fairness-Aware Node Representation Learning
• FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing
• Fairness-aware Message Passing for Graph Neural Networks

Cited by in corpus (4)

• A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability
• Causal invariant geographic network representations with feature and structural distribution shifts
• Counterfactual Learning on Graphs: A Survey
• Causal Inference with Latent Variables: Recent Advances and Future Prospectives