Unsupervised Attributed Multiplex Network Embedding

TL;DR

This paper introduces DMGI, an unsupervised method for embedding attributed multiplex networks that effectively captures multiple relation types and node attributes, outperforming existing methods in various tasks.

Contribution

The paper proposes DMGI, a novel unsupervised embedding approach that integrates multiple relation types and node attributes using mutual information maximization, consensus regularization, and attention mechanisms.

Findings

DMGI outperforms state-of-the-art methods on multiple downstream tasks.

The attention mechanism identifies important relation types for filtering.

DMGI effectively models global properties of multiplex networks.

Abstract

Nodes in a multiplex network are connected by multiple types of relations. However, most existing network embedding methods assume that only a single type of relation exists between nodes. Even for those that consider the multiplexity of a network, they overlook node attributes, resort to node labels for training, and fail to model the global properties of a graph. We present a simple yet effective unsupervised network embedding method for attributed multiplex network called DMGI, inspired by Deep Graph Infomax (DGI) that maximizes the mutual information between local patches of a graph, and the global representation of the entire graph. We devise a systematic way to jointly integrate the node embeddings from multiple graphs by introducing 1) the consensus regularization framework that minimizes the disagreements among the relation-type specific node embeddings, and 2) the universal discriminator that discriminates true samples regardless of the relation types. We also show that the attention mechanism infers the importance of each relation type, and thus can be useful for filtering unnecessary relation types as a preprocessing step. Extensive experiments on various downstream tasks demonstrate that DMGI outperforms the state-of-the-art methods, even though DMGI is fully unsupervised.