TY - GEN
T1 - Individual Fairness for Graph Neural Networks
T2 - 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, KDD 2021
AU - Dong, Yushun
AU - Kang, Jian
AU - Tong, Hanghang
AU - Li, Jundong
N1 - Funding Information:
This material is, in part, supported by the National Science Foundation (NSF) under grant number 2006844 and 1939725. We would like to thank the anonymous reviewers for their constructive feedback.
Publisher Copyright:
© 2021 ACM.
PY - 2021/8/14
Y1 - 2021/8/14
N2 - Recent years have witnessed the pivotal role of Graph Neural Networks (GNNs) in various high-stake decision-making scenarios due to their superior learning capability. Close on the heels of the successful adoption of GNNs in different application domains has been the increasing societal concern that conventional GNNs often do not have fairness considerations. Although some research progress has been made to improve the fairness of GNNs, these works mainly focus on the notion of group fairness regarding different subgroups defined by a protected attribute such as gender, age, and race. Beyond that, it is also essential to study the GNN fairness at a much finer granularity (i.e., at the node level) to ensure that GNNs render similar prediction results for similar individuals to achieve the notion of individual fairness. Toward this goal, in this paper, we make an initial investigation to enhance the individual fairness of GNNs and propose a novel ranking based framework - -REDRESS. Specifically, we refine the notion of individual fairness from a ranking perspective, and formulate the ranking based individual fairness promotion problem. This naturally addresses the issue of Lipschitz constant specification and distance calibration resulted from the Lipschitz condition in the conventional individual fairness definition. Our proposed framework REDRESS encapsulates the GNN model utility maximization and the ranking-based individual fairness promotion in a joint framework to enable end-to-end training. It is noteworthy mentioning that REDRESS is a plug-and-play framework and can be easily generalized to any prevalent GNN architectures. Extensive experiments on multiple real-world graphs demonstrate the superiority of REDRESS in achieving a good balance between model utility maximization and individual fairness promotion. Our open source code can be found here: https://github.com/yushundong/REDRESS.
AB - Recent years have witnessed the pivotal role of Graph Neural Networks (GNNs) in various high-stake decision-making scenarios due to their superior learning capability. Close on the heels of the successful adoption of GNNs in different application domains has been the increasing societal concern that conventional GNNs often do not have fairness considerations. Although some research progress has been made to improve the fairness of GNNs, these works mainly focus on the notion of group fairness regarding different subgroups defined by a protected attribute such as gender, age, and race. Beyond that, it is also essential to study the GNN fairness at a much finer granularity (i.e., at the node level) to ensure that GNNs render similar prediction results for similar individuals to achieve the notion of individual fairness. Toward this goal, in this paper, we make an initial investigation to enhance the individual fairness of GNNs and propose a novel ranking based framework - -REDRESS. Specifically, we refine the notion of individual fairness from a ranking perspective, and formulate the ranking based individual fairness promotion problem. This naturally addresses the issue of Lipschitz constant specification and distance calibration resulted from the Lipschitz condition in the conventional individual fairness definition. Our proposed framework REDRESS encapsulates the GNN model utility maximization and the ranking-based individual fairness promotion in a joint framework to enable end-to-end training. It is noteworthy mentioning that REDRESS is a plug-and-play framework and can be easily generalized to any prevalent GNN architectures. Extensive experiments on multiple real-world graphs demonstrate the superiority of REDRESS in achieving a good balance between model utility maximization and individual fairness promotion. Our open source code can be found here: https://github.com/yushundong/REDRESS.
KW - graph neural networks
KW - individual fairness
KW - ranking
UR - http://www.scopus.com/inward/record.url?scp=85114944463&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85114944463&partnerID=8YFLogxK
U2 - 10.1145/3447548.3467266
DO - 10.1145/3447548.3467266
M3 - Conference contribution
AN - SCOPUS:85114944463
T3 - Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining
SP - 300
EP - 310
BT - KDD 2021 - Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining
PB - Association for Computing Machinery
Y2 - 14 August 2021 through 18 August 2021
ER -