GFairHint: Improving Individual Fairness for Graph Neural Networks via Fairness Hint

by   Paiheng Xu, et al.

Given the growing concerns about fairness in machine learning and the impressive performance of Graph Neural Networks (GNNs) on graph data learning, algorithmic fairness in GNNs has attracted significant attention. While many existing studies improve fairness at the group level, only a few works promote individual fairness, which renders similar outcomes for similar individuals. A desirable framework that promotes individual fairness should (1) balance between fairness and performance, (2) accommodate two commonly-used individual similarity measures (externally annotated and computed from input features), (3) generalize across various GNN models, and (4) be computationally efficient. Unfortunately, none of the prior work achieves all the desirables. In this work, we propose a novel method, GFairHint, which promotes individual fairness in GNNs and achieves all aforementioned desirables. GFairHint learns fairness representations through an auxiliary link prediction task, and then concatenates the representations with the learned node embeddings in original GNNs as a "fairness hint". Through extensive experimental investigations on five real-world graph datasets under three prevalent GNN models covering both individual similarity measures above, GFairHint achieves the best fairness results in almost all combinations of datasets with various backbone models, while generating comparable utility results, with much less computational cost compared to the previous state-of-the-art (SoTA) method.


page 1

page 2

page 3

page 4


On the Interaction between Node Fairness and Edge Privacy in Graph Neural Networks

Due to the emergence of graph neural networks (GNNs) and their widesprea...

Fairness-Aware Graph Neural Networks: A Survey

Graph Neural Networks (GNNs) have become increasingly important due to t...

FairEdit: Preserving Fairness in Graph Neural Networks through Greedy Graph Editing

Graph Neural Networks (GNNs) have proven to excel in predictive modeling...

FairMod: Fair Link Prediction and Recommendation via Graph Modification

As machine learning becomes more widely adopted across domains, it is cr...

Analyzing the Effect of Sampling in GNNs on Individual Fairness

Graph neural network (GNN) based methods have saturated the field of rec...

FairNeuron: Improving Deep Neural Network Fairness with Adversary Games on Selective Neurons

With Deep Neural Network (DNN) being integrated into a growing number of...

EqGNN: Equalized Node Opportunity in Graphs

Graph neural networks (GNNs), has been widely used for supervised learni...

Please sign up or login with your details

Forgot password? Click here to reset