Fast Community Detection based on Graph Autoencoder Reconstruction

TL;DR

This paper introduces GAER, a scalable graph autoencoder framework for fast community detection in large networks, achieving significant speed improvements and high accuracy without prior information.

Contribution

The paper presents a novel, scalable graph autoencoder-based community detection method that reduces complexity and supports real-time updates, outperforming existing approaches.

Findings

GAER reduces complexity from O(N^2) to O(N).

Supports incremental community detection for real-time updates.

Achieves 6.15 to 14.03 times faster inference on large datasets.

Abstract

With the rapid development of big data, how to efficiently and accurately discover tight community structures in large-scale networks for knowledge discovery has attracted more and more attention. In this paper, a community detection framework based on Graph AutoEncoder Reconstruction (noted as GAER) is proposed for the first time. GAER is a highly scalable framework which does not require any prior information. We decompose the graph autoencoder-based one-step encoding into the two-stage encoding framework to adapt to the real-world big data system by reducing complexity from the original O(N^2) to O(N). At the same time, based on the advantages of GAER support module plug-and-play configuration and incremental community detection, we further propose a peer awareness based module for real-time large graphs, which can realize the new nodes community detection at a faster speed, and accelerate model inference with the 6.15 times - 14.03 times speed. Finally, we apply the GAER on multiple real-world datasets, including some large-scale networks. The experimental result verified that GAER has achieved the superior performance on almost all networks.