Variational Embeddings for Community Detection and Node Representation

In this paper, we study how to simultaneously learn two highly correlated tasks of graph analysis, i.e., community detection and node representation learning. We propose an efficient generative model called VECODER for jointly learning Variational Embeddings for Community Detection and node Representation. VECODER assumes that every node can be a member of one or more communities. The node embeddings are learned in such a way that connected nodes are not only “closer” to each other but also share similar community assignments. A joint learning framework leverages community-aware node embeddings for better community detection. We demonstrate on several graph datasets that VECODER effectively outperforms many competitive baselines on all three tasks i.e. node classification, overlapping community detection and non-overlapping community detection. We also show that VECODER is computationally efficient and has quite robust performance with varying hyperparameters.

[1]  Chih-Jen Lin,et al.  LIBLINEAR: A Library for Large Linear Classification , 2008, J. Mach. Learn. Res..

[2]  Jure Leskovec,et al.  Overlapping community detection at scale: a nonnegative matrix factorization approach , 2013, WSDM.

[3]  Charles A. Sutton,et al.  GEMSEC: Graph Embedding with Self Clustering , 2018, 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[4]  Jure Leskovec,et al.  Community Detection in Networks with Node Attributes , 2013, 2013 IEEE 13th International Conference on Data Mining.

[5]  Xinbing Wang,et al.  CommunityGAN: Community Detection with Generative Adversarial Nets , 2019, WWW.

[6]  Daniel R. Figueiredo,et al.  struc2vec: Learning Node Representations from Structural Identity , 2017, KDD.

[7]  T. Vicsek,et al.  Clique percolation in random networks. , 2005, Physical review letters.

[8]  Sune Lehmann,et al.  Link communities reveal multiscale complexity in networks , 2009, Nature.

[9]  Ben Poole,et al.  Categorical Reparameterization with Gumbel-Softmax , 2016, ICLR.

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

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

[12]  Qiongkai Xu,et al.  GraRep: Learning Graph Representations with Global Structural Information , 2015, CIKM.

[13]  Huan Liu,et al.  Leveraging social media networks for classification , 2011, Data Mining and Knowledge Discovery.

[14]  Stephan Günnemann,et al.  Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking , 2017, ICLR.

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

[16]  Jure Leskovec,et al.  Defining and evaluating network communities based on ground-truth , 2012, Knowledge and Information Systems.

[17]  Max Welling,et al.  Semi-Supervised Classification with Graph Convolutional Networks , 2016, ICLR.

[18]  Ruslan Salakhutdinov,et al.  Revisiting Semi-Supervised Learning with Graph Embeddings , 2016, ICML.

[19]  Martin Kleinsteuber,et al.  Epitomic Variational Graph Autoencoder , 2021, 2020 25th International Conference on Pattern Recognition (ICPR).

[20]  Alexander J. Smola,et al.  Neural Information Processing Systems , 1997, NIPS 1997.

[21]  Xiaochun Cao,et al.  Modularity Based Community Detection with Deep Learning , 2016, IJCAI.

[22]  Maosong Sun,et al.  A Unified Framework for Community Detection and Network Representation Learning , 2016, IEEE Transactions on Knowledge and Data Engineering.

[23]  David M Blei,et al.  Efficient discovery of overlapping communities in massive networks , 2013, Proceedings of the National Academy of Sciences.

[24]  Samuel S. Schoenholz,et al.  Neural Message Passing for Quantum Chemistry , 2017, ICML.

[25]  Ludovic Denoyer,et al.  Temporal link prediction by integrating content and structure information , 2011, CIKM '11.

[26]  Carl Doersch,et al.  Tutorial on Variational Autoencoders , 2016, ArXiv.

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

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

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

[30]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[31]  Jure Leskovec,et al.  Learning to Discover Social Circles in Ego Networks , 2012, NIPS.

[32]  Jian Pei,et al.  Community Preserving Network Embedding , 2017, AAAI.

[33]  Geoffrey E. Hinton,et al.  Visualizing Data using t-SNE , 2008 .

[34]  Shie Mannor,et al.  Community Detection via Measure Space Embedding , 2015, NIPS.

[35]  Jure Leskovec,et al.  {SNAP Datasets}: {Stanford} Large Network Dataset Collection , 2014 .

[36]  Jian Tang,et al.  vGraph: A Generative Model for Joint Community Detection and Node Representation Learning , 2019, NeurIPS.

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

[38]  Charu C. Aggarwal,et al.  Node Classification in Signed Social Networks , 2016, SDM.