KDD 2017 Tutorial Proposal

Network Embedding: Enabling Network Analytics and Inference in Vector Space

Peng Cui (cuip@tsinghua.edu.cn), Tsinghua University, China

Jian Pei (jpei@cs.sfu.ca), Simon Fraser University and Huawei Technologies, Canada

Wenwu Zhu (wwzhu@tsinghua.edu.cn), Tsinghua University, China

Abstract

Nowadays, larger and larger, more and more sophisticated networks are used in more and more applications. It is well recognized that network data is sophisticated and challenging. To process graph data effectively, the first critical challenge is network data representation, that is, how to represent networks properly so that advanced analytic tasks, such as pattern discovery, analysis and prediction, can be conducted efficiently in both time and space. In this tutorial, we will review the recent thoughts and achievements on network embedding. More specifically, a series of fundamental problems in network embedding will be discussed, including why we need to revisit network representation, what are the research goals of network embedding, how network embedding can be learned, and the major future directions of network embedding.

Topic Overview

The complexity of big network data has posed significant research challenges to representation learning for networks. In order to support network analytics and inference in the embedding space, the embedding space should be able to reconstruct the original networks, reflect the structural characteristics of the original networks, and maintain the network properties. In this tutorial, we aim to examine some recent advances in network embedding, and more specifically along different goals. This research topic often serves as the basis of a few key techniques in many applications, such as social network analysis, recommender systems and bioinformatics. It is of paramount significance for both research community and industry.

Slides

Coming soon...

Tutors

Peng Cui

Peng Cui is an Associate Professor in Tsinghua University. He got his PhD degree from Tsinghua University in 2010. His research interests include network representation learning, social dynamics modeling and human behavioral modeling. He has published more than 60 papers in prestigious conferences and journals in data mining and multimedia. His recent research won the ICDM 2015 Best Student Paper Award, SIGKDD 2014 Best Paper Finalist, IEEE ICME 2014 Best Paper Award, ACM MM12 Grand Challenge Multimodal Award, and MMM13 Best Paper Award. He is the Area Chair of ICDM 2016, ACM MM 2014-2015, IEEE ICME 2014-2015, ICASSP 2013, Associate Editor of IEEE TKDE, ACM TOMM, Elsevier Journal on Neurocomputing. He was the recipient of ACM China Rising Star Award in 2015. More details.

Jiawei Han

Jian Pei is currently the Canada Research Chair in Big Data Science, a professor in the School of Computing Science and an associate member in the Department of Statistics and Actuarial Science and Faculty of Health Sciences at Simon Fraser University, Canada. In his current sabbatical leave, he is acting as a Technical VP and the Chief Data Scientist of the Central Software Institute of Huawei Technologies. His expertise is in developing business driven, technology enabled data analytics for critical applications. His publications have been cited by more than 65,000 in literature, and by more than 30,000 since 2012. He has an h-index of 72. He is also active in providing consulting service to industry and transferring his research outcome to industry and applications. His leadership in creating industry relationship was highlighted by national news media. During his current sabbatical leave, he is acting as the Chief Data Scientist of Huawei Central Software Institute and is responsible for the development of the AI platform at Huawei. He is an editor of several esteemed journals in his areas and a passionate organizer of the premier academic conferences defining the frontiers of the areas. He received a few prestigious awards, including the 2014 IEEE ICDM Research Contributions Award and the 2015 ACM SIGKDD Service Award. He is a fellow of both ACM and IEEE. More details.

Wenwu Zhu

Wenwu Zhu is with Computer Science Department of Tsinghua University as Professor of “1000 People Plan” of China. Prior to his current post, he was a Senior Researcher and Research Manager at Microsoft Research Asia. He was the Chief Scientist and the Director at Intel Research China from 2004 to 2008. He worked at Bell Labs New Jersey as Member of Technical Staff during 1996-1999. Wenwu Zhu is an IEEE Fellow, SPIE Fellow and ACM Distinguished Scientist. He has published over 200 referred papers in the areas of multimedia computing, communications and networking. He is inventor or co-inventor of over 40 patents. His current research interests are in the area of social media computing and multimedia communications and networking. He served(s) on various editorial boards, such as Guest Editor for the Proceedings of the IEEE, IEEE T-CSVT, and IEEE JSAC; Associate Editor for IEEE Transactions on Mobile Computing, IEEE Transactions on Multimedia, and IEEE Transactions on Circuits and Systems for Video Technology. He served as TPC Co-Chair of IEEE ISCAS 2013 and serves as TPC Co-Chair for ACM Multimedia 2014. More details.

References

[1]    Aditya Grover and Jure Leskovec. 2016. node2vec: Scalable feature learning for networks. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 855–864.

[2]  Bryan Perozzi, Rami Al-Rfou, and Steven Skiena. 2014. Deepwalk: Online learning of social representations. In Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 701–710.

[3]    Shuicheng Yan, Dong Xu, Benyu Zhang, Hong-Jiang Zhang, Qiang Yang, and Stephen Lin. 2007. Graph embedding and extensions: a general framework for dimensionality reduction. Pattern Analysis and Machine Intelligence, IEEE Transactions on 29, 1 (2007), 40–51.

[4]    Christopher C Paige and Michael A Saunders. 1981. Towards a generalized singular value decomposition. SIAM J. Numer. Anal. 18, 3 (1981), 398–405.

[5]    Xiao Wang, Peng Cui, Jing Wang, Jian Pei, Wenwu Zhu, Shiqiang Yang. Community Preserving Network Embedding. AAAI, 2017.

[6]    Peter D Hoff. 2009. Multiplicative latent factor models for description and prediction of social networks. Computational and Mathematical Organization Theory 15, 4 (2009), 261–272.

[7]    Daixin Wang, Peng Cui, Wenwu Zhu. Structural Deep Network Embedding. KDD, 2016.

[8]    Ting Guo, Xingquan Zhu, Jian Pei, and Chengqi Zhang. 2014. Snoc: streaming network node classification. In Data Mining (ICDM), 2014 IEEE International Conference on. IEEE, 150–159.

[9]    Mingdong Ou, Peng Cui, Jian Pei, Wenwu Zhu. Asymmetric Transitivity Preserving Graph Embedding. KDD, 2016.

[10] Dashun Wang, Dino Pedreschi, Chaoming Song, Fosca Giannotti, and Albert- Laszlo Barabasi. 2011. Human mobility, social ties, and link prediction. In Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining. ACM, 1100–1108.

[11] Mingdong Ou, Peng Cui, Fei Wang, Jun Wang, Wenwu Zhu. Non-transitive Hashing with Latent Similarity Components. ACM SIGKDD, 2015.

[12] Mingdong Ou, Peng Cui, Jun Wang, Fei Wang, Wenwu Zhu. Probabilistic Attributed Hashing. AAAI, 2015.

[13] Gilbert W Stewart and Ji-Guang Sun. 1990. Matrix Perturbation Theory (Computer Science and Scientific Computing). (1990).

[14] Mingdong Ou, Peng Cui, Fei Wang, Jun Wang, Wenwu Zhu, Shiqiang Yang. Comparing Apples to Oranges: A Scalable Solution with Heterogeneous Hashing. ACM SIGKDD, 2013.

[15] David Liben-Nowell and Jon Kleinberg. 2007. The link-prediction problem for social networks. journal of the Association for Information Science and Technology 58, 7 (2007), 1019–1031.

[16] Daixin Wang, Peng Cui, Mingdong Ou, Wenwu Zhu. Deep Multimodal Hashing with Orthogonal Regularization. IJCAI, 2015.

[17] Daixin Wang, Peng Cui, Mingdong Ou, Wenwu Zhu. Learning Compact Hash Codes for Multimodal Representations using Orthogonal Deep Structure. IEEE Transactions on Multimedia, 2015.

[18] S. Cao, W. Lu, and Q. Xu. Grarep: Learning graph representations with global structural information. CIKM 2015.

[19] J. Tang, M. Qu, M. Wang, M. Zhang, J. Yan, and Q. Mei. Line: Large-scale information network embedding. WWW 2015.

[20] S. Chang, G.-J. Qi, C. C. Aggarwal, J. Zhou, M. Wang, and T. S. Huang. Factorized similarity learning in networks. ICDM 2014.