Boosting nonnegative matrix factorization based community detection with graph attention auto-encoder

Chaobo He, Yulong Zheng, Xiang Fei, Hanchao Li, Zeng Hu, Yong Tang

Research output: Contribution to journalArticlepeer-review

17 Citations (Scopus)
357 Downloads (Pure)


Community detection is of great help to understand the structures and functions of complex networks. It has become one of popular research topics in the field of complex networks analysis. Due to the simplicity, flexibility, effectiveness and interpretability, Nonnegative Matrix Factorization (NMF)-based methods have been widely employed for community detection. However, most existing NMF-based community detection methods are linear and their performance is limited when facing networks with diversified structure information. In view of this, we propose a nonlinear NMF-based method named NMFGAAE, which is composed of two main modules: NMF and Graph Attention Auto-Encoder (GAAE). This approach can boost the performance of NMF-based community detection methods by the aid of graph neural networks and deep clustering. More specifically, GAAE introduces an attention mechanism directed by NMF-based community detection to learn the node representations, while NMF can simultaneously factor these representations to uncover the community structure. We design a unified framework to jointly optimize GAAE and NMF modules, which is very beneficial to obtain better community detection results. We conduct extensive experiments on synthetic and real-world networks. The results show that NMFGAAE not only performs better than state-of-the-art NMF-based community detection methods, but also outperforms some network representation based baselines.
Original languageEnglish
Pages (from-to)968-981
Number of pages14
Journal IEEE Transactions on Big Data
Issue number4
Early online date12 Aug 2021
Publication statusPublished - 1 Aug 2022

Bibliographical note

© 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.


National Natural Science Foundation of China (Grant Number: 62077045)


  • Complex networks
  • Convolution
  • Task analysis
  • Data models
  • Graph neural networks
  • Feature extraction
  • Big Data


Dive into the research topics of 'Boosting nonnegative matrix factorization based community detection with graph attention auto-encoder'. Together they form a unique fingerprint.

Cite this