Subgroup Generalization and Fairness of Graph Neural Networks: Paper and Code

Get our free extension to see links to code for papers anywhere online!Free add-on: code for papers everywhere!Free add-on: See code for papers anywhere!

Add to Chrome

Add to Firefox

Add to Edge

Subgroup Generalization and Fairness of Graph Neural Networks

Jun 29, 2021

Jiaqi Ma, Junwei Deng, Qiaozhu Mei

Figure 1 for Subgroup Generalization and Fairness of Graph Neural Networks

Figure 2 for Subgroup Generalization and Fairness of Graph Neural Networks

Figure 3 for Subgroup Generalization and Fairness of Graph Neural Networks

Figure 4 for Subgroup Generalization and Fairness of Graph Neural Networks

Share this with someone who'll enjoy it:

Despite enormous successful applications of graph neural networks (GNNs) recently, theoretical understandings of their generalization ability, especially for node-level tasks where data are not independent and identically-distributed (IID), have been sparse. The theoretical investigation of the generalization performance is beneficial for understanding fundamental issues (such as fairness) of GNN models and designing better learning methods. In this paper, we present a novel PAC-Bayesian analysis for GNNs under a non-IID semi-supervised learning setup. Moreover, we analyze the generalization performances on different subgroups of unlabeled nodes, which allows us to further study an accuracy-(dis)parity-style (un)fairness of GNNs from a theoretical perspective. Under reasonable assumptions, we demonstrate that the distance between a test subgroup and the training set can be a key factor affecting the GNN performance on that subgroup, which calls special attention to the training node selection for fair learning. Experiments across multiple GNN models and datasets support our theoretical results.

View paper on

OpenReview

Share this with someone who'll enjoy it: