Graph Community Infomax

Graph representation learning aims at learning low-dimension representations for nodes in graphs, and has been proven very useful in several downstream tasks. In this article, we propose a new model, Graph Community Infomax (GCI), that can adversarial learn representations for nodes in attributed networks. Different from other adversarial network embedding models, which would assume that the data follow some prior distributions and generate fake examples, GCI utilizes the community information of networks, using nodes as positive(or real) examples and negative(or fake) examples at the same time. An autoencoder is applied to learn the embedding vectors for nodes and reconstruct the adjacency matrix, and a discriminator is used to maximize the mutual information between nodes and communities. Experiments on several real-world and synthetic networks have shown that GCI outperforms various network embedding methods on community detection tasks.

[1]  Philip S. Yu,et al.  A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning , 2021, IEEE Transactions on Knowledge and Data Engineering.

[2]  Ge Zhang,et al.  Detecting Communities with Multiplex Semantics by Distinguishing Background, General, and Specialized Topics , 2020, IEEE Transactions on Knowledge and Data Engineering.

[3]  Lina Yao,et al.  Adversarially Regularized Graph Autoencoder , 2018, IJCAI.

[4]  Jeffrey Dean,et al.  Efficient Estimation of Word Representations in Vector Space , 2013, ICLR.

[5]  Jian Yu,et al.  Node Attribute-enhanced Community Detection in Complex Networks , 2017, Scientific Reports.

[6]  Mingzhe Wang,et al.  LINE: Large-scale Information Network Embedding , 2015, WWW.

[7]  M E J Newman,et al.  Modularity and community structure in networks. , 2006, Proceedings of the National Academy of Sciences of the United States of America.

[8]  Pietro Liò,et al.  Deep Graph Infomax , 2018, ICLR.

[9]  Xueqi Cheng,et al.  A Non-negative Symmetric Encoder-Decoder Approach for Community Detection , 2017, CIKM.

[10]  Minnan Luo,et al.  Graph Representation Learning via Graphical Mutual Information Maximization , 2020, WWW.

[11]  Charu C. Aggarwal,et al.  Learning Deep Network Representations with Adversarially Regularized Autoencoders , 2018, KDD.

[12]  Stephan Günnemann,et al.  Overlapping Community Detection with Graph Neural Networks , 2018, ArXiv.

[13]  Kevin Chen-Chuan Chang,et al.  Learning Community Embedding with Community Detection and Node Embedding on Graphs , 2017, CIKM.

[14]  Jure Leskovec,et al.  node2vec: Scalable Feature Learning for Networks , 2016, KDD.

[15]  Jie Zhang,et al.  Semi-supervised Learning on Graphs with Generative Adversarial Nets , 2018, CIKM.

[16]  Pietro Liò,et al.  Spatio-Temporal Deep Graph Infomax , 2019, ArXiv.

[17]  Lise Getoor,et al.  Collective Classification in Network Data , 2008, AI Mag..

[18]  Xiaobao Wang,et al.  Robust Detection of Link Communities With Summary Description in Social Networks , 2021, IEEE Transactions on Knowledge and Data Engineering.

[19]  Ziqiang Weng,et al.  Adversarial Attention-Based Variational Graph Autoencoder , 2020, IEEE Access.

[20]  Thomas S. Huang,et al.  Graph Regularized Nonnegative Matrix Factorization for Data Representation. , 2011, IEEE transactions on pattern analysis and machine intelligence.

[21]  Jian Pei,et al.  Asymmetric Transitivity Preserving Graph Embedding , 2016, KDD.

[22]  Ivan Herman,et al.  Graph Visualization and Navigation in Information Visualization: A Survey , 2000, IEEE Trans. Vis. Comput. Graph..

[23]  Steven Skiena,et al.  DeepWalk: online learning of social representations , 2014, KDD.

[24]  Shu Wu,et al.  CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning , 2020, ArXiv.

[25]  Weixiong Zhang,et al.  Modeling with Node Popularities for Autonomous Overlapping Community Detection , 2020, ACM Trans. Intell. Syst. Technol..

[26]  Wenwu Zhu,et al.  Structural Deep Network Embedding , 2016, KDD.