提出新模型H2SGNN，解决异质图中节点属性差异大的难题。
Addressing Graph Heterogeneity and Heterophily from A Spectral Perspective
- 从谱视角设计双模块：局部独立滤波与全局混合滤波
- 在4个数据集上表现更优，参数和内存消耗更低
- 适合处理复杂异质异配图，如社交网络、知识图谱
图神经网络（GNN）在半监督节点分类任务中表现优异，但仍面临异质性和异配性两大挑战。异质性指图中存在多种类型的节点或边，异配性则指相连节点更可能具有不同属性或标签。现有研究要么仅关注特定元路径的异配性，表达能力不足；要么表达能力强但未能利用高阶邻居。本文提出异质异配谱图神经网络（H2SGNN），包含局部独立滤波与全局混合滤波两个模块：前者自适应学习不同同配程度下的节点表示，后者利用高阶邻居挖掘更多可能的元路径。在四个数据集上的大量实验验证了H2SGNN的有效性，其性能更优且参数与内存开销更低。代码已开源：https://github.com/Lukangkang123/H2SGNN/
原文摘要 · Abstract (English)
Graph neural networks (GNNs) have demonstrated excellent performance in semi-supervised node classification tasks. Despite this, two primary challenges persist: heterogeneity and heterophily. Each of these two challenges can significantly hinder the performance of GNNs. Heterogeneity refers to a graph with multiple types of nodes or edges, while heterophily refers to the fact that connected nodes are more likely to have dissimilar attributes or labels. Although there have been few works studying heterogeneous heterophilic graphs, they either only consider the heterophily of specific meta-paths and lack expressiveness, or have high expressiveness but fail to exploit high-order neighbors. In this paper, we propose a Heterogeneous Heterophilic Spectral Graph Neural Network (H2SGNN), which employs two modules: local independent filtering and global hybrid filtering. Local independent filtering adaptively learns node representations under different homophily, while global hybrid filtering exploits high-order neighbors to learn more possible meta-paths. Extensive experiments are conducted on four datasets to validate the effectiveness of the proposed H2SGNN, which achieves superior performance with fewer parameters and memory consumption. The code is available at the GitHub repo: https://github.com/Lukangkang123/H2SGNN/.
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。