Exploring Topological Bias in Heterogeneous Graph Neural Networks

TL;DR

This paper investigates topological bias in Heterogeneous Graph Neural Networks (HGNNs), demonstrating its universal presence and proposing a contrastive learning method to mitigate bias and improve performance.

Contribution

It introduces a novel approach using meta-weighting and PageRank to identify topological bias in HGNNs and proposes a debiasing contrastive learning framework.

Findings

Topological bias exists universally in HGNNs.

The proposed method improves HGNN performance.

Debiasing enhances model fairness and accuracy.

Abstract

Graph Neural Networks (GNNs) are characterized by their capacity of processing graph-structured data. However, due to the sparsity of labels under semi-supervised learning, they have been found to exhibit biased performance on specific nodes. This kind of bias has been validated to correlate with topological structure and is considered as a bottleneck of GNNs' performance. Existing work focuses on the study of homogeneous GNNs and little attention has been given to topological bias in Heterogeneous Graph Neural Networks (HGNNs). In this work, firstly, in order to distinguish distinct meta relations, we apply meta-weighting to the adjacency matrix of a heterogeneous graph. Based on the modified adjacency matrix, we leverage PageRank along with the node label information to construct a projection. The constructed projection effectively maps nodes to values that strongly correlated with model performance when using datasets both with and without intra-type connections, which demonstrates the universal existence of topological bias in HGNNs. To handle this bias, we propose a debiasing structure based on the difference in the mapped values of nodes and use it along with the original graph structure for contrastive learning. Experiments on three public datasets verify the effectiveness of the proposed method in improving HGNNs' performance and debiasing.