REGAL: Representation Learning-based Graph Alignment

TL;DR

REGAL introduces a novel framework leveraging unsupervised node representation learning to efficiently and accurately align nodes across multiple large-scale networks, outperforming existing methods in speed and accuracy.

Contribution

The paper presents REGAL, a new framework that uses learned node embeddings for network alignment, including the innovative xNetMF formulation for multi-network problems.

Findings

REGAL runs up to 30x faster than comparable methods.

Outperforms existing network alignment methods by 20-30% in accuracy.

Scales to networks with millions of nodes.

Abstract

Problems involving multiple networks are prevalent in many scientific and other domains. In particular, network alignment, or the task of identifying corresponding nodes in different networks, has applications across the social and natural sciences. Motivated by recent advancements in node representation learning for single-graph tasks, we propose REGAL (REpresentation learning-based Graph ALignment), a framework that leverages the power of automatically-learned node representations to match nodes across different graphs. Within REGAL we devise xNetMF, an elegant and principled node embedding formulation that uniquely generalizes to multi-network problems. Our results demonstrate the utility and promise of unsupervised representation learning-based network alignment in terms of both speed and accuracy. REGAL runs up to 30x faster in the representation learning stage than comparable methods, outperforms existing network alignment methods by 20 to 30% accuracy on average, and scales to networks with millions of nodes each.