NetSimile: A Scalable Approach to Size-Independent Network Similarity

TL;DR

NetSimile is a scalable, size-independent method for assessing similarity between networks without node correspondence, enabling various graph mining tasks efficiently.

Contribution

It introduces a novel, scalable approach for network similarity that is size-invariant and does not require node correspondence, outperforming baseline methods.

Findings

NetSimile accurately measures network similarity across diverse sizes.

It is computationally efficient, with linear complexity in the number of edges.

The method enables effective clustering, visualization, and transfer learning tasks.

Abstract

Given a set of k networks, possibly with different sizes and no overlaps in nodes or edges, how can we quickly assess similarity between them, without solving the node-correspondence problem? Analogously, how can we extract a small number of descriptive, numerical features from each graph that effectively serve as the graph's "signature"? Having such features will enable a wealth of graph mining tasks, including clustering, outlier detection, visualization, etc. We propose NetSimile -- a novel, effective, and scalable method for solving the aforementioned problem. NetSimile has the following desirable properties: (a) It gives similarity scores that are size-invariant. (b) It is scalable, being linear on the number of edges for "signature" vector extraction. (c) It does not need to solve the node-correspondence problem. We present extensive experiments on numerous synthetic and real graphs from disparate domains, and show NetSimile's superiority over baseline competitors. We also show how NetSimile enables several mining tasks such as clustering, visualization, discontinuity detection, network transfer learning, and re-identification across networks.