Interpretable and Efficient Heterogeneous Graph Convolutional Network

Graph Convolutional Network (GCN) has achieved extraordinary success in learning effective task-specific representations of nodes graphs. However, regarding Heterogeneous Information (HIN), existing HIN-oriented GCN methods still suffer from two deficiencies: (1) they cannot flexibly explore all possible meta-paths and extract the most useful ones for a target object, which hinders both effectiveness interpretability; (2) often need to generate intermediate meta-path based dense graphs, leads high computational complexity. To address above issues, we propose an interpretable efficient (ie-HGCN) learn objects HINs. It is designed as hierarchical aggregation architecture, i.e., object-level first, followed by type-level aggregation. The novel architecture can automatically each object (within length limit), brings good model interpretability. also reduce cost avoiding HIN transformation neighborhood attention. We provide theoretical analysis about proposed ie-HGCN terms evaluating usefulness meta-paths, its connection spectral graph convolution on HINs, quasi-linear time Extensive experiments three real network datasets demonstrate superiority over state-of-the-art methods.