Home >

news Help

Publication Information


Title
Japanese: 
English:Learning Community Structure with Variational Autoencoder 
Author
Japanese: Choong Jun Jin, Liu Xin, 村田剛志.  
English: Jun Jin Choong, Liu Xin, Tsuyoshi MURATA.  
Language English 
Journal/Book name
Japanese: 
English:Proceedings of IEEE International Conference on Data Mining (ICDM 2018) 
Volume, Number, Page         pp. 69-78
Published date Nov. 17, 2018 
Publisher
Japanese: 
English:IEEE 
Conference name
Japanese: 
English:IEEE International Conference on Data Mining (ICDM 2018) 
Conference site
Japanese: 
English:Singapore 
Official URL https://ieeexplore.ieee.org/document/8594831
 
DOI https://doi.org/10.1109/ICDM.2018.00022
Abstract Discovering community structure in networks remains a fundamentally challenging task. From scientific domains such as biology, chemistry and physics to social networks the challenge of identifying community structures in different kinds of network is challenging since there is no universal definition of community structure. Furthermore, with the surge of social networks, content information has played a pivotal role in defining community structure, demanding techniques beyond its traditional approach. Recently, network representation learning have shown tremendous promise. Leveraging on recent advances in deep learning, one can exploit deep learning's superiority to a network problem. Most predominantly, successes in supervised and semi-supervised task has shown promising results in network representation learning tasks such as link prediction and graph classification. However, much has yet to be explored in the literature of community detection which is an unsupervised learning task. This paper proposes a deep generative model for community detection and network generation. Empowered with Bayesian deep learning, deep generative models are capable of exploiting non-linearities while giving insights in terms of uncertainty. Hence, this paper proposes Variational Graph Autoencoder for Community Detection (VGAECD). Extensive experiment shows that it is capable of outperforming existing state-of-the-art methods. The generalization of the proposed model also allows the model to be considered as a graph generator. Additionally, unlike traditional methods, the proposed model does not require a predefined community structure definition. Instead, it assumes the existence of latent similarity between nodes and allows the model to find these similarities through an automatic model selection process. Optionally, it is capable of exploiting feature-rich information of a network such as node content, further increasing its performance.

©2007 Tokyo Institute of Technology All rights reserved.