论文标题
通过学习拓扑空间和特征空间的学习表示形式，在图形卷积网络中重新访问异性
Revisiting Heterophily in Graph Convolution Networks by Learning Representations Across Topological and Feature Spaces
论文作者
论文摘要
图形卷积网络（GCN）在基于几个基于图的机器学习任务的学习表示方面取得了巨大成功。特定于学习丰富的节点表示，大多数方法仅依赖于同义假设，并且在异性图上的性能有限。虽然已经开发了几种使用新体系结构来解决异质的方法，但我们认为，通过学习两个空间的图表表示，即拓扑和特征空间GCN可以异源性地解决。在这项工作中，我们通过实验表明，通过学习和组合整个拓扑空间和特征空间中的表示形式，通过学习和结合表示形式，在同粒和异质图基准上进行了半监督的节点分类任务的性能。
Graph convolution networks (GCNs) have been enormously successful in learning representations over several graph-based machine learning tasks. Specific to learning rich node representations, most of the methods have solely relied on the homophily assumption and have shown limited performance on the heterophilous graphs. While several methods have been developed with new architectures to address heterophily, we argue that by learning graph representations across two spaces i.e., topology and feature space GCNs can address heterophily. In this work, we experimentally demonstrate the performance of the proposed GCN framework over semi-supervised node classification task on both homophilous and heterophilous graph benchmarks by learning and combining representations across the topological and the feature spaces.
