MGAE: marginalized graph autoencoder for graph clustering

Chun Wang, Shirui Pan, Guodong Long, Xingquan Zhu, Jing Jiang

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

75 Citations (Scopus)


Graph clustering aims to discover community structures in networks, the task being fundamentally challenging mainly because the topology structure and the content of the graphs are dicult to represent for clustering analysis. Recently, graph clustering has moved from traditional shallow methods to deep learning approaches, thanks to the unique feature representation learning capability of deep learning. However, existing deep approaches for graph clustering can only exploit the structure information, while ignoring the content information associated with the nodes in a graph. In this paper, we propose a novel marginalized graph autoencoder (MGAE) algorithm for graph clustering. The key innovation of MGAE is that it advances the autoencoder to the graph domain, so graph representation learning can be carried out not only in a purely unsupervised by leveraging structure and content information, it can also be stacked in a deep fashion to learn effective representation. From a technical viewpoint, we propose a marginalized graph convolutional network to corrupt network node content, allowing node content to interact with network features, and marginalizes the corrupted features in a graph autoencoder context to learn graph feature representations. The learned features are fed into the spectral clustering algorithm for graph clustering. Experimental results on benchmark datasets demonstrate the superior performance of MGAE, compared to numerous baselines.

Original languageEnglish
Title of host publicationCIKM'17 - Proceedings of the 2017 ACM Conference on Information and Knowledge Management
Subtitle of host publicationNovember 6–10, 2017 Singapore, Singapore
EditorsMark Sanderson, Ada Fu, Jimeng Sun
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Number of pages10
ISBN (Electronic)9781450349185
Publication statusPublished - 2017
Externally publishedYes
EventACM International Conference on Information and Knowledge Management 2017 - Singapore, Singapore
Duration: 6 Nov 201710 Nov 2017
Conference number: 26th


ConferenceACM International Conference on Information and Knowledge Management 2017
Abbreviated titleCIKM 2017
Internet address


  • Autoencoder
  • Graph autoencoder
  • Graph clustering
  • Graph convolutional network
  • Network representation

Cite this