Meta-Path-Free Representation Learning on Heterogeneous Networks

TL;DR

This paper introduces HCN, a novel meta-path-free method for representation learning on heterogeneous networks that captures structural and semantic information without relying on meta-paths, outperforming existing methods.

Contribution

The paper presents the first meta-path-free approach, HCN, using a $k$-strata algorithm to effectively learn from heterogeneous networks without experience-based meta-path selection.

Findings

HCN significantly outperforms state-of-the-art methods

Effective capture of $k$-hop structural and semantic information

Validated on three real-world heterogeneous networks

Abstract

Real-world networks and knowledge graphs are usually heterogeneous networks. Representation learning on heterogeneous networks is not only a popular but a pragmatic research field. The main challenge comes from the heterogeneity -- the diverse types of nodes and edges. Besides, for a given node in a HIN, the significance of a neighborhood node depends not only on the structural distance but semantics. How to effectively capture both structural and semantic relations is another challenge. The current state-of-the-art methods are based on the algorithm of meta-path and therefore have a serious disadvantage -- the performance depends on the arbitrary choosing of meta-path(s). However, the selection of meta-path(s) is experience-based and time-consuming. In this work, we propose a novel meta-path-free representation learning on heterogeneous networks, namely Heterogeneous graph Convolutional Networks (HCN). The proposed method fuses the heterogeneity and develops a $k$-strata algorithm ($k$ is an integer) to capture the $k$-hop structural and semantic information in heterogeneous networks. To the best of our knowledge, this is the first attempt to break out of the confinement of meta-paths for representation learning on heterogeneous networks. We carry out extensive experiments on three real-world heterogeneous networks. The experimental results demonstrate that the proposed method significantly outperforms the current state-of-the-art methods in a variety of analytic tasks.