Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity

TL;DR

This paper presents UGRAPHEMB, an unsupervised, inductive framework for embedding entire graphs into a vector space, preserving graph-graph proximity and enabling various graph analysis tasks.

Contribution

The paper introduces UGRAPHEMB, a novel unsupervised and inductive method for graph-level embedding that utilizes Multi-Scale Node Attention for improved representation quality.

Findings

Achieves competitive accuracy in graph classification

Effective in similarity ranking tasks

Facilitates graph visualization

Abstract

We introduce a novel approach to graph-level representation learning, which is to embed an entire graph into a vector space where the embeddings of two graphs preserve their graph-graph proximity. Our approach, UGRAPHEMB, is a general framework that provides a novel means to performing graph-level embedding in a completely unsupervised and inductive manner. The learned neural network can be considered as a function that receives any graph as input, either seen or unseen in the training set, and transforms it into an embedding. A novel graph-level embedding generation mechanism called Multi-Scale Node Attention (MSNA), is proposed. Experiments on five real graph datasets show that UGRAPHEMB achieves competitive accuracy in the tasks of graph classification, similarity ranking, and graph visualization.