Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
This addresses degree bias in graph learning for node classification tasks, representing an incremental improvement over existing Graph Contrastive Learning methods.
The paper tackles degree bias in Graph Neural Networks for node classification by proposing a Hardness Adaptive Reweighted contrastive loss that adds positive pairs using labels and adaptively weights them, achieving better performance across four datasets at global and degree levels.
Graph Neural Networks (GNNs) often suffer from degree bias in node classification tasks, where prediction performance varies across nodes with different degrees. Several approaches, which adopt Graph Contrastive Learning (GCL), have been proposed to mitigate this bias. However, the limited number of positive pairs and the equal weighting of all positives and negatives in GCL still lead to low-degree nodes acquiring insufficient and noisy information. This paper proposes the Hardness Adaptive Reweighted (HAR) contrastive loss to mitigate degree bias. It adds more positive pairs by leveraging node labels and adaptively weights positive and negative pairs based on their learning hardness. In addition, we develop an experimental framework named SHARP to extend HAR to a broader range of scenarios. Both our theoretical analysis and experiments validate the effectiveness of SHARP. The experimental results across four datasets show that SHARP achieves better performance against baselines at both global and degree levels.