Contrastive Representation Learning Based on Multiple Node-centered Subgraphs

TL;DR

This paper introduces a novel self-supervised graph contrastive learning method that leverages multiple node-centered subgraphs to improve node representations, achieving state-of-the-art results on various datasets.

Contribution

It proposes a new contrastive learning framework based on multiple node-centered subgraphs, enhancing node representation learning in graph-structured data.

Findings

Achieved state-of-the-art results on real-world datasets.

Effectively maximized mutual information between subgraphs.

Improved downstream task performance.

Abstract

As the basic element of graph-structured data, node has been recognized as the main object of study in graph representation learning. A single node intuitively has multiple node-centered subgraphs from the whole graph (e.g., one person in a social network has multiple social circles based on his different relationships). We study this intuition under the framework of graph contrastive learning, and propose a multiple node-centered subgraphs contrastive representation learning method to learn node representation on graphs in a self-supervised way. Specifically, we carefully design a series of node-centered regional subgraphs of the central node. Then, the mutual information between different subgraphs of the same node is maximized by contrastive loss. Experiments on various real-world datasets and different downstream tasks demonstrate that our model has achieved state-of-the-art results.