COIN: Co-Cluster Infomax for Bipartite Graphs

TL;DR

COIN introduces a co-cluster infomax framework for bipartite graphs that captures cluster-level information by maximizing mutual information of co-clusters, improving node embedding quality in various applications.

Contribution

This paper proposes a novel end-to-end co-cluster infomax method for bipartite graphs that simplifies mutual information estimation and provides theoretical guarantees.

Findings

COIN effectively increases mutual information of node embeddings.

COIN outperforms existing methods on benchmark datasets.

Theoretical analysis confirms COIN's ability to enhance embedding quality.

Abstract

Bipartite graphs are powerful data structures to model interactions between two types of nodes, which have been used in a variety of applications, such as recommender systems, information retrieval, and drug discovery. A fundamental challenge for bipartite graphs is how to learn informative node embeddings. Despite the success of recent self-supervised learning methods on bipartite graphs, their objectives are discriminating instance-wise positive and negative node pairs, which could contain cluster-level errors. In this paper, we introduce a novel co-cluster infomax (COIN) framework, which captures the cluster-level information by maximizing the mutual information of co-clusters. Different from previous infomax methods which estimate mutual information by neural networks, COIN could easily calculate mutual information. Besides, COIN is an end-to-end coclustering method which can be trained jointly with other objective functions and optimized via back-propagation. Furthermore, we also provide theoretical analysis for COIN. We theoretically prove that COIN is able to effectively increase the mutual information of node embeddings and COIN is upper-bounded by the prior distributions of nodes. We extensively evaluate the proposed COIN framework on various benchmark datasets and tasks to demonstrate the effectiveness of COIN.