提出双频过滤自感知GNN，同时处理同质与异质图的表征难题
Dual-Frequency Filtering Self-aware Graph Neural Networks for Homophilic and Heterophilic Graphs
- 引入高低频滤波器分离拓扑特征，按频率约束减少噪声冗余
- 动态调整滤波比例，统一适配同质与异质图结构，提升分类准确率
- 通过频带间动态对齐缓解拓扑与属性干扰，适合复杂图数据建模
图神经网络在处理图结构数据方面表现优异，但面临两大挑战：拓扑与属性间的干扰扭曲节点表示，以及多数GNN具有低通滤波特性，导致忽略图信号中的高频有用信息，尤其在异质图中更为突出。为此，本文提出双频过滤自感知图神经网络（DFGNN），通过集成低通与高通滤波器，提取平滑与细节化的拓扑特征，并利用频带特定约束最小化各频段的噪声与冗余。模型动态调节滤波比例以适应同质与异质图。此外，通过拓扑与属性在各自频带间的动态对应关系，缓解二者干扰，提升整体性能与表达能力。在基准数据集上的大量实验表明，DFGNN在分类性能上优于现有先进方法，验证了其在处理同质与异质图方面的有效性。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have excelled in handling graph-structured data, attracting significant research interest. However, two primary challenges have emerged: interference between topology and attributes distorting node representations, and the low-pass filtering nature of most GNNs leading to the oversight of valuable high-frequency information in graph signals. These issues are particularly pronounced in heterophilic graphs. To address these challenges, we propose Dual-Frequency Filtering Self-aware Graph Neural Networks (DFGNN). DFGNN integrates low-pass and high-pass filters to extract smooth and detailed topological features, using frequency-specific constraints to minimize noise and redundancy in the respective frequency bands. The model dynamically adjusts filtering ratios to accommodate both homophilic and heterophilic graphs. Furthermore, DFGNN mitigates interference by aligning topological and attribute representations through dynamic correspondences between their respective frequency bands, enhancing overall model performance and expressiveness. Extensive experiments conducted on benchmark datasets demonstrate that DFGNN outperforms state-of-the-art methods in classification performance, highlighting its effectiveness in handling both homophilic and heterophilic graphs.
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。