Heterogeneous graph convolutional network with local influence

doi:10.1016/j.knosys.2021.107699

Heterogeneous graph convolutional network with local influence

2022-01-01

12

PRE

AI

DOI：10.1016/j.knosys.2021.107699

原文链接

原文求助

摘要

En 中文

Graph convolutional networks (GCNs) have recently drawn extensive attention due to their superior learning performance on graph data. Through graph convolution, topological structure and node attributes can be simultaneously aggregated in a local neighborhood. In heterogeneous information networks (HINs), the diversity of node and edge types poses great challenges to graph convolution. This paper proposes a heterogeneous graph convolutional network based on local influence (named HIGCN), which aims to discriminatively aggregate structural information, attribute information and multi-semantic information in HINs. Here, local influence refers to the influence of neighborhood nodes on the central node. Firstly, a HIGCN block is constructed, in which the local influence is calculated through a heuristic structural influence strategy proposed in this paper and an attention-based attribute influence strategy. Afterwards, 1 x 1 convolution is innovatively used to fuse the embeddings under multiple semantics. Finally, the entire HIGCN framework is constructed by stacking HIGCN blocks. Experiments on real-world network datasets show that HIGCN achieves higher accuracy than related methods in various downstream tasks (node classification, link prediction, etc.), which verifies the effectiveness of the structural influence strategy and the semantic fusion method. (C) 2021 Elsevier B.V. All rights reserved.

Keyword:

Heterogeneous information networks

Graph convolutional networks

Local influence

Network representation learning

Heterogeneous graph convolutional network with local influence

摘要

期刊

机构

引用论文