Refining Network Alignment to Improve Matched Neighborhood Consistency

TL;DR

This paper introduces RefiNA, a scalable refinement method that enhances network alignment accuracy by improving matched neighborhood consistency, significantly boosting performance across various unsupervised methods especially in challenging topologically diverse graphs.

Contribution

The paper proposes RefiNA, a simple, scalable post hoc refinement technique that improves existing network alignment methods by focusing on matched neighborhood consistency.

Findings

RefiNA increases alignment accuracy by up to 90%.

It enables alignment of graphs with 5x topological differences.

RefiNA is compatible with any unsupervised network alignment method.

Abstract

Network alignment, or the task of finding meaningful node correspondences between nodes in different graphs, is an important graph mining task with many scientific and industrial applications. An important principle for network alignment is matched neighborhood consistency (MNC): nodes that are close in one graph should be matched to nodes that are close in the other graph. We theoretically demonstrate a close relationship between MNC and alignment accuracy. As many existing network alignment methods struggle to preserve topological consistency in difficult scenarios, we show how to refine their solutions by improving their MNC. Our refinement method, RefiNA, is straightforward to implement, admits scalable sparse approximation, and can be paired post hoc with any network alignment method. Extensive experiments show that RefiNA increases the accuracy of diverse unsupervised network alignment methods by up to 90%, making them robust enough to align graphs that are 5x more topologically different than were considered in prior work.