Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization

TL;DR

This paper introduces GraPHmax, an unsupervised graph neural network that combines hierarchical structure and mutual information maximization to generate effective vector representations of entire graphs, outperforming existing methods.

Contribution

It proposes a novel unsupervised framework integrating hierarchical GNNs and periphery-based mutual information maximization for graph representation learning.

Findings

Outperforms state-of-the-art on multiple graph classification tasks

Effective in unsupervised setting without labeled data

Competitive results on various real-world datasets

Abstract

Deep representation learning on non-Euclidean data types, such as graphs, has gained significant attention in recent years. Invent of graph neural networks has improved the state-of-the-art for both node and the entire graph representation in a vector space. However, for the entire graph representation, most of the existing graph neural networks are trained on a graph classification loss in a supervised way. But obtaining labels of a large number of graphs is expensive for real world applications. Thus, we aim to propose an unsupervised graph neural network to generate a vector representation of an entire graph in this paper. For this purpose, we combine the idea of hierarchical graph neural networks and mutual information maximization into a single framework. We also propose and use the concept of periphery representation of a graph and show its usefulness in the proposed algorithm which is referred as GraPHmax. We conduct thorough experiments on several real-world graph datasets and compare the performance of GraPHmax with a diverse set of both supervised and unsupervised baseline algorithms. Experimental results show that we are able to improve the state-of-the-art for multiple graph level tasks on several real-world datasets, while remain competitive on the others.