With the rapid development of the World Wide Web (WWW), heterogeneous graphs (HG) have explosive growth. Recently, heterogeneous graph neural network (HGNN) has shown great potential in learning on HG. Current studies of HGNN mainly focus on some HGs with strong homophily properties (nodes connected by meta-path tend to have the same labels), while few discussions are made in those that are less homophilous. Recently, there have been many works on homogeneous graphs with heterophily. However, due to heterogeneity, it is non-trivial to extend their approach to deal with HGs with heterophily. In this work, based on empirical observations, we propose a meta-path-induced metric to measure the homophily degree of a HG. We also find that current HGNNs may have degenerated performance when handling HGs with less homophilous properties. Thus it is essential to increase the generalization ability of HGNNs on non-homophilous HGs. To this end, we propose HDHGR, a homophily-oriented deep heterogeneous graph rewiring approach that modifies the HG structure to increase the performance of HGNN. We theoretically verify HDHGR. In addition, experiments on real-world HGs demonstrate the effectiveness of HDHGR, which brings at most more than 10% relative gain.

翻译：随着万维网的快速发展，异构图的规模呈爆炸式增长。近年来，异构图神经网络在学习异构图方面展现出巨大潜力。当前异构图神经网络的研究主要聚焦于具有强同质性属性的异构图（通过元路径连接的节点倾向于具有相同标签），而对同质性较弱图的研究较少。近期已涌现众多针对非同质同构图的处理方法。然而，由于异构性，将其方法扩展至处理非同质异构图并非易事。本文基于实证观察，提出一种由元路径驱动的异构图同质性度量指标。同时发现现有异构图神经网络在处理低同质性异构图时可能出现性能退化。因此，提升异构图神经网络在非同质异构图上的泛化能力至关重要。为此，本文提出HDHGR——一种面向同质性的深度异构图边重连方法，通过修改异构图结构提升异构图神经网络的性能。我们通过理论验证了HDHGR的有效性。在真实异构图上的实验进一步证明了HDHGR的优越性，其相对性能增益最高超过10%。