Mitigating Degree Bias in Graph Representation Learning with Learnable Structural Augmentation and Structural Self-Attention
This work addresses degree fairness in graph representation learning, which is crucial for applications like social networks and recommendation systems, but it is incremental as it builds on existing transformer and augmentation methods.
The paper tackles the problem of degree bias in Graph Neural Networks (GNNs), where high-degree nodes dominate message passing, leading to under-representation of low-degree nodes, by proposing DegFairGT, a Degree Fairness Graph Transformer that uses learnable structural augmentation and structural self-attention to mitigate bias, achieving state-of-the-art results in fairness, classification, and clustering tasks across six datasets.
Graph Neural Networks (GNNs) update node representations through message passing, which is primarily based on the homophily principle, assuming that adjacent nodes share similar features. However, in real-world graphs with long-tailed degree distributions, high-degree nodes dominate message passing, causing a degree bias where low-degree nodes remain under-represented due to inadequate messages. The main challenge in addressing degree bias is how to discover non-adjacent nodes to provide additional messages to low-degree nodes while reducing excessive messages for high-degree nodes. Nevertheless, exploiting non-adjacent nodes to provide valuable messages is challenging, as it could generate noisy information and disrupt the original graph structures. To solve it, we propose a novel Degree Fairness Graph Transformer, named DegFairGT, to mitigate degree bias by discovering structural similarities between non-adjacent nodes through learnable structural augmentation and structural self-attention. Our key idea is to exploit non-adjacent nodes with similar roles in the same community to generate informative edges under our augmentation, which could provide informative messages between nodes with similar roles while ensuring that the homophily principle is maintained within the community. To enable DegFairGT to learn such structural similarities, we then propose a structural self-attention to capture the similarities between node pairs. To preserve global graph structures and prevent graph augmentation from hindering graph structure, we propose a Self-Supervised Learning task to preserve p-step transition probability and regularize graph augmentation. Extensive experiments on six datasets showed that DegFairGT outperformed state-of-the-art baselines in degree fairness analysis, node classification, and node clustering tasks.