TY - GEN
T1 - Towards Fair Graph Neural Networks via Graph Counterfactual
AU - Guo, Zhimeng
AU - Li, Jialiang
AU - Xiao, Teng
AU - Ma, Yao
AU - Wang, Suhang
N1 - Publisher Copyright:
© 2023 Copyright held by the owner/author(s).
PY - 2023/10/21
Y1 - 2023/10/21
N2 - 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.
AB - 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.
KW - Causal learning
KW - Counterfactual fairness
KW - Graph neural networks
UR - http://www.scopus.com/inward/record.url?scp=85178102342&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85178102342&partnerID=8YFLogxK
U2 - 10.1145/3583780.3615092
DO - 10.1145/3583780.3615092
M3 - Conference contribution
AN - SCOPUS:85178102342
T3 - International Conference on Information and Knowledge Management, Proceedings
SP - 669
EP - 678
BT - CIKM 2023 - Proceedings of the 32nd ACM International Conference on Information and Knowledge Management
PB - Association for Computing Machinery
T2 - 32nd ACM International Conference on Information and Knowledge Management, CIKM 2023
Y2 - 21 October 2023 through 25 October 2023
ER -