论文标题
HP-GMN：用于异质图的图形存储网络
HP-GMN: Graph Memory Networks for Heterophilous Graphs
论文作者
论文摘要
图神经网络（GNN）在各种图形问题中取得了巨大成功。但是，大多数GNN是基于同质假设传递神经网络（MPNN）的消息，其中具有相同标签的节点在图中连接。现实世界中的问题给我们带来了异质问题，其中具有不同标签的节点在图中连接。 MPNN无法解决异质问题，因为它们混合了来自不同分布的信息，并且不擅长捕获全球模式。因此，我们研究了本文中异性疾病问题的新型图存储网络模型（HP-GMN）。在HP-GMN中，本地统计数据和内存以促进预测来学习本地信息和全局模式。我们进一步提出正规化术语，以帮助记忆学习全球信息。我们进行了广泛的实验，以表明我们的方法在同粒细胞和异性图上都达到了最先进的性能。
Graph neural networks (GNNs) have achieved great success in various graph problems. However, most GNNs are Message Passing Neural Networks (MPNNs) based on the homophily assumption, where nodes with the same label are connected in graphs. Real-world problems bring us heterophily problems, where nodes with different labels are connected in graphs. MPNNs fail to address the heterophily problem because they mix information from different distributions and are not good at capturing global patterns. Therefore, we investigate a novel Graph Memory Networks model on Heterophilous Graphs (HP-GMN) to the heterophily problem in this paper. In HP-GMN, local information and global patterns are learned by local statistics and the memory to facilitate the prediction. We further propose regularization terms to help the memory learn global information. We conduct extensive experiments to show that our method achieves state-of-the-art performance on both homophilous and heterophilous graphs.
