Deep Network Embedding for Graph Representation Learning in Signed Networks

Network embedding has attracted an increasing attention over the past few years. As an effective approach to solve graph mining problems, network embedding aims to learn a low-dimensional feature vector representation for each node of a given network. The vast majority of existing network embedding algorithms, however, are only designed for unsigned networks, and the signed networks containing both positive and negative links, have pretty distinct properties from the unsigned counterpart. In this paper, we propose a deep network embedding model to learn the low-dimensional node vector representations with structural balance preservation for the signed networks. The model employs a semisupervised stacked auto-encoder to reconstruct the adjacency connections of a given signed network. As the adjacency connections are overwhelmingly positive in the real-world signed networks, we impose a larger penalty to make the auto-encoder focus more on reconstructing the scarce negative links than the abundant positive links. In addition, to preserve the structural balance property of signed networks, we design the pairwise constraints to make the positively connected nodes much closer than the negatively connected nodes in the embedding space. Based on the network representations learned by the proposed model, we conduct link sign prediction and community detection in signed networks. Extensive experimental results in real-world datasets demonstrate the superiority of the proposed model over the state-of-the-art network embedding algorithms for graph representation learning in signed networks.

[1]  Matthias Hein,et al.  Clustering Signed Networks with the Geometric Mean of Laplacians , 2016, NIPS.

[2]  Clara Pizzuti,et al.  Community mining in signed networks: A multiobjective approach , 2013, 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM 2013).

[3]  Jane You,et al.  Adaptive Ensembling of Semi-Supervised Clustering Solutions , 2017, IEEE Transactions on Knowledge and Data Engineering.

[4]  Ghazaleh Beigi,et al.  Exploiting Emotional Information for Trust/Distrust Prediction , 2016, SDM.

[5]  Charu C. Aggarwal,et al.  Heterogeneous Network Embedding via Deep Architectures , 2015, KDD.

[6]  Korris Fu-Lai Chung,et al.  Deep Network Embedding with Aggregated Proximity Preserving , 2017, 2017 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM).

[7]  Wei Xiong,et al.  Stacked Convolutional Denoising Auto-Encoders for Feature Representation , 2017, IEEE Transactions on Cybernetics.

[8]  Christian Bauckhage,et al.  The slashdot zoo: mining a social network with negative edges , 2009, WWW.

[9]  James A. Davis.  Clustering and Structural Balance in Graphs , 1977 .

[10]  Wei Lu,et al.  Deep Neural Networks for Learning Graph Representations , 2016, AAAI.

[11]  Enhong Chen,et al.  Learning Deep Representations for Graph Clustering , 2014, AAAI.

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

[13]  Charu C. Aggarwal,et al.  Signed Network Embedding in Social Media , 2017, SDM.

[14]  Faïez Gargouri,et al.  Group extraction from professional social network using a new semi-supervised hierarchical clustering , 2013, Knowledge and Information Systems.

[15]  Ping He,et al.  Semi-supervised clustering via multi-level random walk , 2014, Pattern Recognit..

[16]  John Blitzer,et al.  Co-Training for Domain Adaptation , 2011, NIPS.

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

[18]  Yoshua Bengio,et al.  Greedy Layer-Wise Training of Deep Networks , 2006, NIPS.

[19]  Yoshua Bengio,et al.  Domain Adaptation for Large-Scale Sentiment Classification: A Deep Learning Approach , 2011, ICML.

[20]  F. Harary.  On the notion of balance of a signed graph. , 1953 .

[21]  Michal Pilipczuk,et al.  Sitting Closer to Friends than Enemies, Revisited , 2014, Theory of Computing Systems.

[22]  Ke Lu,et al.  Transfer Independently Together: A Generalized Framework for Domain Adaptation , 2019, IEEE Transactions on Cybernetics.

[23]  Jiming Liu,et al.  Community Mining from Signed Social Networks , 2007, IEEE Transactions on Knowledge and Data Engineering.

[24]  Jure Leskovec,et al.  Predicting positive and negative links in online social networks , 2010, WWW '10.

[25]  Sabato Marco Siniscalchi,et al.  Adaptation to New Microphones Using Artificial Neural Networks With Trainable Activation Functions , 2017, IEEE Transactions on Neural Networks and Learning Systems.

[26]  Hareton K. N. Leung,et al.  Incremental Semi-Supervised Clustering Ensemble for High Dimensional Data Clustering , 2016, IEEE Transactions on Knowledge and Data Engineering.

[27]  Inderjit S. Dhillon,et al.  Scalable clustering of signed networks using balance normalized cut , 2012, CIKM.

[28]  Luc Van Gool,et al.  The Pascal Visual Object Classes (VOC) Challenge , 2010, International Journal of Computer Vision.

[29]  Jure Leskovec,et al.  Signed networks in social media , 2010, CHI.

[30]  Charu C. Aggarwal,et al.  A Survey of Signed Network Mining in Social Media , 2015, ACM Comput. Surv..

[31]  Noah E. Friedkin,et al.  Network Studies of Social Influence , 1993 .

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

[33]  C. Altafini,et al.  Computing global structural balance in large-scale signed social networks , 2011, Proceedings of the National Academy of Sciences.

[34]  Inderjit S. Dhillon,et al.  Low rank modeling of signed networks , 2012, KDD.

[35]  Dan Klein,et al.  From Instance-level Constraints to Space-Level Constraints: Making the Most of Prior Knowledge in Data Clustering , 2002, ICML.

[36]  Pablo Jensen,et al.  Analysis of community structure in networks of correlated data. , 2008, Physical review. E, Statistical, nonlinear, and soft matter physics.

[37]  Sahin Albayrak,et al.  Spectral Analysis of Signed Graphs for Clustering, Prediction and Visualization , 2010, SDM.

[38]  Jun Zhang,et al.  Adaptive Semi-Supervised Classifier Ensemble for High Dimensional Data Classification , 2019, IEEE Transactions on Cybernetics.

[39]  Ke Lu,et al.  Low-Rank Discriminant Embedding for Multiview Learning , 2017, IEEE Transactions on Cybernetics.

[40]  Yide Wang,et al.  Progressive Semisupervised Learning of Multiple Classifiers , 2018, IEEE Transactions on Cybernetics.

[41]  Charu C. Aggarwal,et al.  Negative Link Prediction in Social Media , 2014, WSDM.

[42]  Korris Fu-Lai Chung,et al.  Leveraging Cross-Network Information for Graph Sparsification in Influence Maximization , 2017, SIGIR.

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

[44]  Francisco Herrera,et al.  Self-labeled techniques for semi-supervised learning: taxonomy, software and empirical study , 2015, Knowledge and Information Systems.

[45]  David B. Skillicorn,et al.  Spectral Embedding of Signed Networks , 2015, SDM.

[46]  Mikhail Belkin,et al.  Laplacian Eigenmaps and Spectral Techniques for Embedding and Clustering , 2001, NIPS.

[47]  Huan Liu,et al.  Is distrust the negation of trust?: the value of distrust in social media , 2014, HT.

[48]  Paolo Avesani,et al.  Controversial Users Demand Local Trust Metrics: An Experimental Study on Epinions.com Community , 2005, AAAI.

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

[50]  Jun Yu,et al.  Coupled Deep Autoencoder for Single Image Super-Resolution , 2017, IEEE Transactions on Cybernetics.

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

[52]  M. McPherson,et al.  Birds of a Feather: Homophily in Social Networks , 2001 .

[53]  Korris Fu-Lai Chung,et al.  Deep Domain Adaptation Based on Multi-layer Joint Kernelized Distance , 2018, SIGIR.

[54]  Jure Leskovec,et al.  Governance in Social Media: A Case Study of the Wikipedia Promotion Process , 2010, ICWSM.