Multi-view contrastive learning for multilayer network embedding

Abstract

Graph embedding aims to learn low-dimension node representations which can be applied to various downstream tasks, such as node clustering and node classification. When it comes to heterogeneous graphs, things get more challenging as the graph contains richer semantic and structural information. Most existing heterogeneous graph embedding methods usually convert the graph into several homogenous graphs, and then use the manual label information to train the model. However, Graph neural networks (GNNs) mostly require task-dependent labels to learn representations, which is even more costly for heterogeneous graphs. Furthermore, these models treat each converted homogenous graph independently while ignoring the inter-layer informative relational clues among the multi-graphs. Inspired by recent advances of Deep Graph Infomax and multi-view learning in homogeneous graph embedding, we propose an unsupervised graph neural network called CL-MNE that adopts multi-view contrastive learning and multilayer information fusion for heterogeneous graph embedding. The proposed model learns rich local and global graph information by maximizing the local-global mutual information from adjacency matrix and diffusion matrix two different views. Moreover, a variant model CL-MNEreg, which provides embedding information of all graph layers, is constructed by addingg a consensus regularization to the CL-MNE. Experiments of node clustering and classification tasks on mainstream datasets demonstrate the effectiveness of the proposed two models.