通过难学节点自适应重加权，缓解图神经网络的度偏差问题。
Mitigating Degree Bias Adaptively with Hard-to-Learn Nodes in Graph Contrastive Learning
- 基于学习难度动态调整正负样本权重，增强低度节点信息获取
- 在四个数据集上同时提升全局与不同度节点的分类准确率
- 适用于各类图对比学习场景，尤其适合低度节点表现差的情况
图神经网络在节点分类任务中常受度偏差影响，即不同度节点的预测性能差异显著。尽管已有基于图对比学习（GCL）的方法尝试缓解此问题，但正样本数量有限且正负样本等权重的设定仍导致低度节点获得的信息不足且噪声大。本文提出硬度自适应重加权（HAR）对比损失，通过利用节点标签增加正样本，并根据学习难度自适应调整正负样本权重。此外，构建了名为SHARP的实验框架，将HAR扩展至更广泛场景。理论分析与实验证明，SHARP在四个数据集上的全局及按度划分的性能均优于基线方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。