Learning Features of Network Structures Using Graphlets

TL;DR

This paper introduces graphlet-based features and methods for network classification, significantly improving performance on static and temporal networks by capturing structural patterns overlooked by existing techniques.

Contribution

It proposes two novel graphlet-based techniques, gl2vec and gl-DCNN, enhancing network classification by leveraging small subgraph patterns.

Findings

Graphlet features improve classification accuracy.

Proposed methods outperform existing approaches.

Effective on both static and temporal networks.

Abstract

Networks are fundamental to the study of complex systems, ranging from social contacts, message transactions, to biological regulations and economical networks. In many realistic applications, these networks may vary over time. Modeling and analyzing such temporal properties is of additional interest as it can provide a richer characterization of relations between nodes in networks. In this paper, we explore the role of \emph{graphlets} in network classification for both static and temporal networks. Graphlets are small non-isomorphic induced subgraphs representing connected patterns in a network and their frequency can be used to assess network structures. We show that graphlet features, which are not captured by state-of-the-art methods, play a significant role in enhancing the performance of network classification. To that end, we propose two novel graphlet-based techniques, \emph{gl2vec} for network embedding, and \emph{gl-DCNN} for diffusion-convolutional neural networks. We demonstrate the efficacy and usability of \emph{gl2vec} and \emph{gl-DCNN} through extensive experiments using several real-world static and temporal networks. We find that features learned from graphlets can bring notable performance increases to state-of-the-art methods in network analysis.