AttrE2vec: Unsupervised Attributed Edge Representation Learning

TL;DR

AttrE2Vec is an unsupervised, inductive method for learning low-dimensional vector representations of edges in attributed networks, capturing topology, attributes, and features to improve downstream tasks.

Contribution

It introduces a novel approach for edge representation learning that is unsupervised and inductive, filling a gap in graph embedding research.

Findings

Outperforms existing methods in edge classification accuracy

Produces more meaningful edge embeddings as shown by clustering analysis

Enhances downstream task performance with higher AUC and accuracy

Abstract

Representation learning has overcome the often arduous and manual featurization of networks through (unsupervised) feature learning as it results in embeddings that can apply to a variety of downstream learning tasks. The focus of representation learning on graphs has focused mainly on shallow (node-centric) or deep (graph-based) learning approaches. While there have been approaches that work on homogeneous and heterogeneous networks with multi-typed nodes and edges, there is a gap in learning edge representations. This paper proposes a novel unsupervised inductive method called AttrE2Vec, which learns a low-dimensional vector representation for edges in attributed networks. It systematically captures the topological proximity, attributes affinity, and feature similarity of edges. Contrary to current advances in edge embedding research, our proposal extends the body of methods providing representations for edges, capturing graph attributes in an inductive and unsupervised manner. Experimental results show that, compared to contemporary approaches, our method builds more powerful edge vector representations, reflected by higher quality measures (AUC, accuracy) in downstream tasks as edge classification and edge clustering. It is also confirmed by analyzing low-dimensional embedding projections.