新模型让图神经网络更好处理方向性与异质邻居。
Directed Homophily-Aware Graph Neural Network
- 用可重置门控机制动态调节消息传递，适应不同同质性。
- 在链接预测上提升最多15.07%，优于现有最佳方法。
- 适合研究方向敏感或异质结构的图数据任务。
图神经网络（GNN）在图结构数据学习任务中表现优异，但多数难以泛化到异质邻居场景，且忽略真实图的有向性，导致在具有非对称结构的有向图上性能不佳。本文提出定向同质性感知图神经网络（DHGNN），通过引入同质性感知和方向敏感组件，解决上述问题。DHGNN采用可重置门控机制，根据同质性水平和信息量自适应调节消息贡献；设计结构感知的抗噪融合模块，有效整合原方向与反向节点表示。在同质与异质有向图数据集上的大量实验表明，DHGNN在节点分类和链接预测任务上均优于现有先进方法，尤其在链接预测上相比最优基线最高提升15.07%。分析显示，门控机制能捕捉方向性同质性差异及层间同质性波动，为复杂图结构上的消息传递行为提供深层洞察。
原文摘要 · Abstract (English)
Graph Neural Networks (GNNs) have achieved significant success in various learning tasks on graph-structured data. Nevertheless, most GNNs struggle to generalize to heterophilic neighborhoods. Additionally, many GNNs ignore the directional nature of real-world graphs, resulting in suboptimal performance on directed graphs with asymmetric structures. In this work, we propose Directed Homophily-aware Graph Neural Network (DHGNN), a novel framework that addresses these limitations by incorporating homophily-aware and direction-sensitive components. DHGNN employs a resettable gating mechanism to adaptively modulate message contributions based on homophily levels and informativeness, and a structure-aware noise-tolerant fusion module to effectively integrate node representations from the original and reverse directions. Extensive experiments on both homophilic and heterophilic directed graph datasets demonstrate that DHGNN outperforms state-of-the-art methods in node classification and link prediction. In particular, DHGNN improves over the best baseline by up to 15.07\% in link prediction. Our analysis further shows that the gating mechanism captures directional homophily gaps and fluctuating homophily across layers, providing deeper insights into message-passing behavior on complex graph structures.
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。