Heterogeneous Graph Contrastive Learning with Spectral Augmentation

TL;DR

This paper introduces a spectral-enhanced contrastive learning model for heterogeneous graphs, incorporating spectral augmentation to better utilize spectral information and improve representation learning in complex, real-world networks.

Contribution

It proposes the first spectral augmentation algorithm for heterogeneous graph neural networks, enhancing spectral information modeling in graph contrastive learning.

Findings

The model outperforms existing methods on multiple real-world datasets.

Spectral augmentation improves the robustness of heterogeneous graph representations.

The approach effectively captures spectral information in heterogeneous graphs.

Abstract

Heterogeneous graphs can well describe the complex entity relationships in the real world. For example, online shopping networks contain multiple physical types of consumers and products, as well as multiple relationship types such as purchasing and favoriting. More and more scholars pay attention to this research because heterogeneous graph representation learning shows strong application potential in real-world scenarios. However, the existing heterogeneous graph models use data augmentation techniques to enhance the use of graph structure information, which only captures the graph structure information from the spatial topology, ignoring the information displayed in the spectrum dimension of the graph structure. To address the issue that heterogeneous graph representation learning methods fail to model spectral information, this paper introduces a spectral-enhanced graph contrastive learning model (SHCL) and proposes a spectral augmentation algorithm for the first time in heterogeneous graph neural networks. The proposed model learns an adaptive topology augmentation scheme through the heterogeneous graph itself, disrupting the structural information of the heterogeneous graph in the spectrum dimension, and ultimately improving the learning effect of the model. Experimental results on multiple real-world datasets demonstrate substantial advantages of the proposed model.