解决图神经网络结构失衡问题，先降异质性再传同质信息。
HeRB: Heterophily-Resolved Structure Balancer for Graph Neural Networks
- 先减少跨类边、增加同类边，降低图的异质性。
- 在异质图上提升准确率，6个异质数据集平均增益超5%。
- 适合处理标签分布不均的复杂图数据，如社交网络、生物分子图。
图神经网络在图数据表征方面取得显著进展，但仍面临结构失衡挑战。现有方法未考虑图的异质性（即相连节点具有不同标签或特征），导致效果受限。我们验证了异质性对结构失衡的影响，提出先缓解异质性，再传递同质知识的思路。为此，设计了HeRB（Heterophily-Resolved Structure Balancer）方法，包含两个创新组件：1）异质性减弱增强模块，用于减少跨类边、增加同类边；2）同质知识传递机制，将头节点的同质信息传递给尾节点。实验表明，HeRB在2个同质和6个异质基准数据集上表现优异，消融实验进一步验证了两个组件的有效性。
原文摘要 · Abstract (English)
Recent research has witnessed the remarkable progress of Graph Neural Networks (GNNs) in the realm of graph data representation. However, GNNs still encounter the challenge of structural imbalance. Prior solutions to this problem did not take graph heterophily into account, namely that connected nodes process distinct labels or features, thus resulting in a deficiency in effectiveness. Upon verifying the impact of heterophily on solving the structural imbalance problem, we propose to rectify the heterophily first and then transfer homophilic knowledge. To the end, we devise a method named HeRB (Heterophily-Resolved Structure Balancer) for GNNs. HeRB consists of two innovative components: 1) A heterophily-lessening augmentation module which serves to reduce inter-class edges and increase intra-class edges; 2) A homophilic knowledge transfer mechanism to convey homophilic information from head nodes to tail nodes. Experimental results demonstrate that HeRB achieves superior performance on two homophilic and six heterophilic benchmark datasets, and the ablation studies further validate the efficacy of two proposed components.
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。