Hybrid Micro/Macro Level Convolution for Heterogeneous Graph Learning
This paper addresses the problem of insufficient utilization of heterogeneous properties, structural information loss, and lack of interpretability in heterogeneous graph representation learning for researchers working with complex, multi-typed graph data.
This paper introduces HGConv, a novel heterogeneous graph convolution approach that learns comprehensive node representations by performing convolutions directly on the intrinsic structure of heterogeneous graphs at both micro and macro levels. Experiments show HGConv outperforms existing methods on various tasks and offers intuitive interpretability for graph analysis.
Heterogeneous graphs are pervasive in practical scenarios, where each graph consists of multiple types of nodes and edges. Representation learning on heterogeneous graphs aims to obtain low-dimensional node representations that could preserve both node attributes and relation information. However, most of the existing graph convolution approaches were designed for homogeneous graphs, and therefore cannot handle heterogeneous graphs. Some recent methods designed for heterogeneous graphs are also faced with several issues, including the insufficient utilization of heterogeneous properties, structural information loss, and lack of interpretability. In this paper, we propose HGConv, a novel Heterogeneous Graph Convolution approach, to learn comprehensive node representations on heterogeneous graphs with a hybrid micro/macro level convolutional operation. Different from existing methods, HGConv could perform convolutions on the intrinsic structure of heterogeneous graphs directly at both micro and macro levels: A micro-level convolution to learn the importance of nodes within the same relation, and a macro-level convolution to distinguish the subtle difference across different relations. The hybrid strategy enables HGConv to fully leverage heterogeneous information with proper interpretability. Moreover, a weighted residual connection is designed to aggregate both inherent attributes and neighbor information of the focal node adaptively. Extensive experiments on various tasks demonstrate not only the superiority of HGConv over existing methods, but also the intuitive interpretability of our approach for graph analysis.