Graph neural networks (GNNs) have shown great prowess in learning representations suitable for numerous graph-based machine learning tasks. When applied to semi-supervised node classification, GNNs are widely believed to work well due to the homophily assumption (``like attracts like''), and fail to generalize to heterophilous graphs where dissimilar nodes connect. Recent works design new architectures to overcome such heterophily-related limitations, citing poor baseline performance and new architecture improvements on a few heterophilous graph benchmark datasets as evidence for this notion. In our experiments, we empirically find that standard graph convolutional networks (GCNs) can actually achieve better performance than such carefully designed methods on some commonly used heterophilous graphs. This motivates us to reconsider whether homophily is truly necessary for good GNN performance. We find that this claim is not quite true, and in fact, GCNs can achieve strong performance on heterophilous graphs under certain conditions. Our work carefully characterizes these conditions, and provides supporting theoretical understanding and empirical observations. Finally, we examine existing heterophilous graphs benchmarks and reconcile how the GCN (under)performs on them based on this understanding.
翻译:用于半监督节点分类时,人们普遍认为,由于同质假设(“类似吸引相似的”),GNN能够产生良好的效果,而且没有概括地归纳出不同节点连接的杂交图。最近的工作设计了新结构,以克服这些与杂交相关的限制,以基准性能欠佳和新结构改进为由,在少数超遗传的图表基准数据集中作为这个概念的证据。在我们的实验中,我们从经验上发现,标准图形共变网络(GCN)实际上能够比一些常用的异性相色图上精心设计的方法取得更好的效果。这促使我们重新考虑同性图对于GNN的表现是否真正必要。我们发现,这一说法并不完全正确,事实上,GCN在某些条件下可以在超异性特征图表上取得很强的性能。我们的工作仔细描述了这些条件,并提供了支持理论理解和经验观察。最后,我们根据这些图表对现有的GPRO基准进行了对比。