Graph Community Infomax

doi:10.1145/3480244

Graph Community Infomax

2021-11-15

4

PRE

AI

DOI：10.1145/3480244

Original request for help

Save

Abstract

En 中文

Graph representation learning aims at learning low-dimension representations for nodes in graphs, and has been proven very useful in several downstream tasks. In this article, we propose a new model, Graph Community Infomax (GCI), that can adversarial learn representations for nodes in attributed networks. Different from other adversarial network embedding models, which would assume that the data follow some prior distributions and generate fake examples, GCI utilizes the community information of networks, using nodes as positive(or real) examples and negative(or fake) examples at the same time. An autoencoder is applied to learn the embedding vectors for nodes and reconstruct the adjacency matrix, and a discriminator is used to maximize the mutual information between nodes and communities. Experiments on several real-world and synthetic networks have shown that GCI outperforms various network embedding methods on community detection tasks.

Keywords:

Mutual information

attributed network

community detecton

representation learning

Graph Community Infomax

Abstract

Journal

Organization