Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning

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 extending HAR to a broader range of scenarios. Both our theoretical analysis and experiments validate the effectiveness of SHARP. Across four datasets, SHARP outperforms baselines in 14 of 16 settings, improving global accuracy on Cora by 3.6% and 4.2% under the GCN and GAT backbones, while at the degree level it raises accuracy for the lowest-degree nodes by over 10%, confirming that the gains are targeted at the low-degree nodes most affected by degree bias.