Towards Fair Graph Neural Networks via Graph Counterfactual

被引:14
作者
Guo, Zhimeng [1 ]
Li, Jialiang [2 ]
Xiao, Teng [1 ]
Ma, Yao [3 ]
Wang, Suhang [1 ]
机构
[1] Penn State Univ, University Pk, PA 16802 USA
[2] New Jersey Inst Technol, Newark, NJ USA
[3] Rensselaer Polytech Inst, Troy, NY USA
来源
PROCEEDINGS OF THE 32ND ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2023 | 2023年
基金
美国国家科学基金会;
关键词
Graph neural networks; Counterfactual fairness; Causal learning;
D O I
10.1145/3583780.3615092
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
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.
引用
收藏
页码:669 / 678
页数:10
相关论文
共 46 条
[1]  
Agarwal C, 2021, PR MACH LEARN RES, V161, P2114
[2]  
Asuncion A., 2007, UCI Machine Learning Repository
[3]   BA-GNN: On Learning Bias-Aware Graph Neural Network [J].
Chen, Zhengyu ;
Xiao, Teng ;
Kuang, Kun .
2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022), 2022, :3012-3024
[4]  
Dai EY, 2023, Arxiv, DOI [arXiv:2204.08570, 10.48550/arXiv.2204.08570, DOI 10.48550/ARXIV.2204.08570]
[5]   Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information [J].
Dai, Enyan ;
Wang, Suhang .
WSDM '21: PROCEEDINGS OF THE 14TH ACM INTERNATIONAL CONFERENCE ON WEB SEARCH AND DATA MINING, 2021, :680-688
[6]  
Dai Enyan, 2023, KDD
[7]   EDITS: Modeling and Mitigating Data Bias for Graph Neural Networks [J].
Dong, Yushun ;
Liu, Ninghao ;
Jalaian, Brian ;
Li, Jundong .
PROCEEDINGS OF THE ACM WEB CONFERENCE 2022 (WWW'22), 2022, :1259-1269
[8]  
Dwork C., 2012, P 3 INNOVATIONS THEO, P214, DOI [10.1145/2090236.2090255, DOI 10.1145/2090236.2090255]
[9]  
Guangyin Jin, 2020, 2020 12th International Conference on Measuring Technology and Mechatronics Automation (ICMTMA). Proceedings, P474, DOI 10.1109/ICMTMA50254.2020.00108
[10]  
Guo ZM, 2024, Arxiv, DOI arXiv:2304.01391