HIN2Grid: A disentangled CNN-based framework for heterogeneous network learning

Ziyang Zhang

doi:10.1016/j.eswa.2021.115823

2022-01-01

PRE

DOI：10.1016/j.eswa.2021.115823

原文链接

原文求助

摘要

En 中文

Recently, graph convolutional networks (GCNs) have been applied to heterogeneous information network (HIN) learning and have shown promising performance. However, the performance of GCNs degrades attributed to the recursive propagation, which leads to an indistinguishable embedding for the distinctly heterogeneous node. Besides, the inherently coupled paradigm of GCNs limits their applications on large-scale graphs. In this paper, we tackle these problems by proposing a disentangled framework named Heterogeneous Information Network to Grid (HIN2Grid) for heterogeneous network learning. We innovatively design an effective and efficient strategy to transform the graph data into semantic-specific grid-like data, which can be effectively processed by convolutional neural networks (CNNs), thus explicitly overcoming the drawbacks of the inherent paradigm of GCNs. Such a CNN-based learning scheme also contributes to extracting more expressive features and consume less time and memory. We further propose dual attention mechanisms to capture the importance of various grid-like data and heterogeneous semantics, thus providing interpretability and robustness for HIN2Grid. We conduct experiments on four datasets and the results show that HIN2Grid significantly outperforms the stateof-the-art methods, gaining a improvement on node classification of about 2% to 10% and a 2 to 5 times promotion on running speed.

Keyword:

Network embedding

Heterogeneous graph learning

Graph convolutional network

Data mining