Please visit my new homepage: www.jian-tang.com

   Jian  Tang (唐建)

  Assistant Professor,

    HEC Montreal & Montreal Institute for Learning Algorithms (MILA)

   Email: tangjianpku at gmail.com,  Weibo@chuckpku, Twitter@tangjianpku, CV


*NEW* If you want to work with me as a postdoc in MILA, please consider applying the postdoctoral scholarship of IVADO (deadline, 15/05/2018).

*NEW* I'm looking for Ph.Ds, masters, visitors, and interns to work with me in the fields of deep learning and reinforcement learning with various applications. If you're interested, please send me an email or apply through the MILA recruitment page.

Research Interest

  • Deep learning, reinforcement learning
  • Graph representation learning and reasoning
  • Recommender systems
  • Natural language understanding
  • Drug discovery

Research Experience

  • 2017.12 - Now  Assistant Professor, HEC Montreal & MILA
  • 2017.9-2017.11 Visiting Scholar, Tsinghua University
  • 2017.4 - 2017.6 Visiting Scholar, Carnegie Mellon University, working with Professor Ruslan Salakhutdinov 
  • 2016.10 - 2017.4 Research Fellow, University of Michigan
  • 2014.7- 2016.10  Associate Researcher II, Microsoft Research Asia
  • 2011.9-2013.8 Visiting student in University of Michigan
  • 2010.9-2011.7  Research assistant in Microsoft Research Asia (MSRA)

Selected Projects

  • Learning representations of networks
  • Learning representations of text
  • Big data visualization
Publications GoogleScholar
  • Jiezhong Qiu, Jian Tang, Hao Ma, Yuxiao Dong, Kuansan Wang, and Jie Tang. DeepInf: Modeling Influence Locality in Large Social Networks. In Proceedings of the Twenty-Fourth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD'18).
  • Minjeong Kim, Minsuk Choi, Sunwoong Lee, Jian Tang, Haesun Park, and Jaegul Choo. PixelSNE: Pixel-Aligned Stochastic Neighbor Embedding for Efficient 2D Visualization with Screen-Resolution Precision. In 20th EG / VGTC Conference on Visualization (EuroVis'18). 
  • Quanyu Dai, Qiang Li, Jian Tang, and Dan Wang. Adversarial Network Embedding, in Proc. of 2018 AAAI Conf. on Artificial Intelligence (AAAI'18), New Orleans, LA, Feb. 2018
  • Luchen Liu, Jianhao Shen, Ming Zhang, Zichang Wang, and Jian Tang. Learning the Joint Representation of Heterogeneous Temporal Events for Clinical Event Prediction, in Proc. of 2018 AAAI Conf. on Artificial Intelligence (AAAI'18), New Orleans, LA, Feb. 2018
  • Meng Qu, Jian Tang, and Jiawei Han, "Curriculum Learning for Heterogeneous Star Network Embedding via Deep Reinforcement Learning",  in Proc. of 2018 ACM  Int. Conf. on Web Search and Data Mining (WSDM'18), Los Angeles, CA, Feb. 2018
  • Meng Qu, Jian Tang, Jingbo Shang, Xiang Ren, Ming Zhang, Jiawei Han. An Attention-based Collaboration Framework for Multi-View Network Representation Learning, in Proc. of 2017 ACM Int. Conf. on Information and Knowledge Management (CIKM'17), Singapore, Nov. 2017
  • Jian Tang, Cheng Li and Qiaozhu Mei. Learning representations of large-scale networks. KDD'17 Tutorial. slides.
  • Jian Tang, Yue Wang, Kai Zheng and Qiaozhu Mei. End-to-end learning for short text expansion. To appear in KDD'17. 
  • Xuanzhe Liu*, Wei Ai*, Huoran Li, Jian Tang, Gang Huang, and Qiaozhu Mei, "Derive User Preferences of Mobile Apps from their Management Activities," in ACM Transactions on Information Systems (TOIS) , in press, 2017.
  • Jian Tang, Jingzhou Liu, Ming Zhang and Qiaozhu Mei. Visualizing Large-scale and High-dimensional Data.  WWW'16.  (Best paper nomination 5/727) slides.  [source code
  • Huoran Li, Wei Ai, Xuanzhe Liu, Jian Tang, Gang Huang, Feng Feng, and Qiaozhu Mei. Voting with Their Feet: Inferring User Preferences from App Management Activities. WWW'16 (industry track).
  • Jian Tang, Meng Qu, and Qiaozhu Mei. PTE: Predictive Text Embedding through Large-scale Heterogeneous Text Networks.  KDD'15. [source code
  • Jian Tang, Meng Qu, Mingzhe Wang, Ming Zhang, Jun Yan and Qiaozhu Mei. LINE: Large-scale Information Network Embedding. WWW'15.  [source code] (Most cited paper in WWW'15)
  • Jian Tang, Ming Zhang, and Qiaozhu Mei. "Look Ma, No Hands!" A parameter-free topic model.  2014
  • Yong Luo, Jian Tang, Jun Yan, Chao Xu, and Zheng Chen. Pre-trained multi-view word embedding using two-side neural network. AAAI'14.
  • Jian Tang, Zhaoshi Meng, XuanLong Nguyen, Qiaozhu Mei and Ming Zhang. Understanding the limiting factors of topic modeling via posterior contraction analysis. In proceedings of the 31st International Conference on Machine Learning (ICML), Beijing, June 2014.
    (Best paper award, 1/1500)
  • Jian Tang, Ming Zhang, and Qiaozhu Mei. One theme in all views: Modeling consensus topics in multiple contexts. In Proceedings of the 2013 ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD’13). (17% acceptance) 
  • Jian Tang, Jun Yan, Lei Ji, Ming Zhang, Shaodan Guo, Ning Liu, Xianfang Wang, and Zheng Chen. Collaborative users' brand preference across multiple domains from implicit feedbacks. AAAI 2011. PP447-482.
  • Jian Tang, Ning Liu, Jun Yan, Yelong Shen, Shaodan Guo, Bin Gao, Shuicheng Yan, and Ming Zhang. Learning to rank audience for behavioral targeting in display ads. CIKM 2011: 605-610
  • Lei Zhang, Jian Tang, and Ming Zhang. Integrating temporal usage pattern into personalized tag prediction. APWeb 2012: 354-365.
  • Ming Zhang, Sheng Feng, Jian Tang, Bolanle Ojokoh, and Guojun Liu. Co-ranking multiple entities in a heterogeneous network: Integrating temporal factor and users' bookmarks. ICADL 2011, Beijing, China. Springer LNCS 7008, PP.202-211.
  • Bolanle Ojokoh, Ming Zhang, and Jian Tang. A trigram hidden Markov model for metadata extraction from heterogeneous references. Information Science , Volume 181, Issue 9, 1 May 2011, Pages 1538-1551 (Elsevier Press).
  • Fei Yan, Ming Zhang, Jian Tang, Tao Sun, Zhi-Hong Deng, and Long Xiao. Users' book-loan behaviors analysis and knowledge dependency mining. WAIM 2010: 206-217.
  • Yan Fei, Zhang Ming, Tan Yuwei, Tang Jian, and Deng Zhihong. Community discovery based on actors' interest and social network structure. In the twenty-seventh National Database Conference of China, 2010. (In Chinese).

  • Program committee: WSDM 2018, AAAI 2018, CAI 2018, WWW 2018, ICML 2018, IJCAI 2018, NIPS 2018, EMNLP 2018, CIKM 2018.
  • Program committee: WWW 2017, AAAI 2017, EACL 2017, IJCAI 2017, KDD 2017, EMNLP 2017, CIKM 2017, BigData 2017, NLPCC 2017
  • Area Chair of "Machine learning and prediction" in National Social Media Processing (SMP 2016)
  • Program committee: WWW2016, ACL2016, IJCAI 2016, EMNLP 2016, ASONAM 2016, NLPCC 2016
  • Program committee:  WWW 2015, EMNLP 2015
  • Reviewer: Transactions on Knowledge and Data Engineering (TKDE), Transactions on the Web (TWeb), Transactions on Information Systems (TOIS), Transactions on Big Data (TBD), Journal of Machine Learning Research (JMLR).
  • Talk "Learning Representations of Graphs" at Google Brain, Montreal, 2018.05.07.
  • Invited talk "Progress and Future Directions of Network Representations" at Machine Intelligence Frontier Seminar 2017, CCF special topic on knowledge graph, 2017.10
  • Invited talk "Towards combining information retrieval and reasoning for natural language understanding", at Tsinghua University, 2017.9.
  • Tutorial “Learning representations of large-scale networks” at KDD 2017, Halifax, Canada, 2017.8
  • Talk "Introduction to Deep Learning & How to Do Research in Machine Learning", at Peking University, 2017.6
  • Talk "Visualizing large-scale and high-dimensional data", at PKU-UCLA Symposium. 2017. 7
  • Talk "Learning representations of large-scale networks", at Peking University, Tsinghua University, JingDong, iFlytek,  TianYanCha, Toutiao AI Lab, 2017.6-7.
  • Talk "Learning representations of large-scale networks", at HEC Montreal.
  • Talk "Learning representations of large-scale networks", at University of Montreal.
  • Talk "Visualizing large-scale and high-dimensional data" at  School of Information, Central University of Finance and Economics, 2016.
  • Talk "Visualizing large-scale and high-dimensional data" at  MOE-Microsoft Key Laboratory of Statistics and Information Technology of Peking University, 2016.
  • Invited talk "Learning text embedding via network embedding" at 9th National R Meeting, 2016. slides.
  • Invited talk "Study on the limiting factors of topic modeling" at the China National Computer Congress (CNCC) 2015.
  • Invited talk "LINE: large-scale information network embedding" at Beijing Institute of Technology, Alibaba Technical Forum. 
  • Oral presentation at KDD 2013, ICML 2014, WWW 2015, KDD 2015.
  • Invited talk "Look Ma, No hands! A parameter-free topic model" at student seminar of statistics department in University of Michigan.
  • Talk "Look Ma, No hands! A parameter-free topic model" at the 4th Michigan data mining workshop.
  •  2009.7 programming language summer school, in University of Oregon.