Graph Neural Networks (GNNs) have garnered significant scholarly attention for their powerful capabilities in modeling graph structures. Despite this, two primary challenges persist: heterogeneity and heterophily. Existing studies often address heterogeneous and heterophilic graphs separately, leaving a research gap in the understanding of heterogeneous heterophilic graphs-those that feature diverse node or relation types with dissimilar connected nodes. To address this gap, we investigate the application of spectral graph filters within heterogeneous graphs. Specifically, we propose a Heterogeneous Heterophilic Spectral Graph Neural Network (H2SGNN), which employs a dual-module approach: local independent filtering and global hybrid filtering. The local independent filtering module applies polynomial filters to each subgraph independently to adapt to different homophily, while the global hybrid filtering module captures interactions across different subgraphs. Extensive empirical evaluations on four real-world datasets demonstrate the superiority of H2SGNN compared to state-of-the-art methods.

本研究聚焦于异质异亲图的挑战，填补了现有研究对这一领域的认识空白。提出的异质异亲谱图神经网络（H2SGNN）结合局部独立过滤和全局混合过滤的双模块方法，能够适应不同的同亲性并捕捉子图之间的交互。大量实证评估表明，H2SGNN在四个真实世界数据集上超越了现有先进方法。

解决图中的异质性和异亲性问题：一种异质异亲谱图神经网络