Mingsheng Long


Mingsheng Long

龙明盛

Associate Professor, Ph.D Supervisor
School of Software, Tsinghua University

Machine Learning Group
National Engineering Lab for Big Data Software

longmingsheng@gmail.com, mingsheng@tsinghua.edu.cn

Room 11-413, East Main Building, Tsinghua University, Beijing, China


Reminder to prospective students: My PhD and Master positions for class 2020 have been filled.

Biography


My current research spans machine learning theories, algorithms, and systems, with special interests in transfer learning, deep learning, and predictive learning. In particular, my research is persistently dedicated to advancing all areas of transfer learning, including domain adaptation, inductive transfer learning, multi-task learning, few-shot learning, and learning to learn.

I am an associate professor and Ph.D supervisor in the School of Software, Tsinghua University. I am leading the Machine Learning Group in the National Engineering Lab for Big Data Software. I am looking for highly motivated graduate or undergraduate students to work on machine learning and its applications in AI and data science. Please email me with curriculum vitae if you are interested.

My Quote

Everything should be made as simple as possible, but no simpler.” --Albert Einstein

Research


Education


Research Experience


Selected Publications [Full List] [DBLP] [Google Scholar]

(* Corresponding Author)


Thesis

  1. Mingsheng Long. Transfer Learning: Problems and Methods. 1-127, 2014 [PDF] (In Chinese)

Preprints

  1. Towards Understanding the Transferability of Deep Representations
    Hong Liu, Mingsheng Long*, Jianmin Wang, Michael I. Jordan [arXiv]

  2. Less Confusion More Transferable: Minimum Class Confusion for Versatile Domain Adaptation
    Ying Jin, Ximei Wang, Mingsheng Long*, Jianmin Wang [arXiv]

  3. Adversarial Pyramid Network for Video Domain Generalization
    Zhiyu Yao, Yunbo Wang, Xingqiang Du, Mingsheng Long*, Jianmin Wang [arXiv]

Journal Articles

  1. Transferable Representation Learning with Deep Adaptation Networks
    Mingsheng Long, Yue Cao, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 41(12):3071-3085, 2019 [Link]

  2. Deep Learning of Transferable Representation for Scalable Domain Adaptation
    Mingsheng Long, Jianmin Wang, Yue Cao, Jiaguang Sun, Philip S. Yu
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 28(8):2027-2040, 2016 [Link] [Code]

  3. Domain Invariant Transfer Kernel Learning
    Mingsheng Long, Jianmin Wang, Jiaguang Sun, Philip S. Yu
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 27(6):1519-1532, 2015 [Link] [Code]

  4. Transfer Learning with Graph Co-Regularization
    Mingsheng Long, Jianmin Wang, Guiguang Ding, Dou Shen, Qiang Yang
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 26(7):1805-1818, 2014 [Link] [Code]

  5. Adaptation Regularization: A General Framework for Transfer Learning
    Mingsheng Long, Jianmin Wang, Guiguang Ding, Sinno Jialin Pan, Philip S. Yu
    IEEE Transactions on Knowledge and Data Engineering (TKDE), 26(5):1076-1089, 2014 [Link] [Code] (ESI Highly Cited Paper)

Conference Proceedings

  1. Catastrophic Forgetting Meets Negative Transfer: Batch Spectral Shrinkage for Safe Transfer Learning
    Xinyang Chen, Sinan Wang, Bo Fu, Mingsheng Long*, Jianmin Wang
    Neural Information Processing Systems (NIPS), 2019 [PDF] [Code]

  2. Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
    Ximei Wang, Ying Jin, Mingsheng Long*, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NIPS), 2019 [PDF] [Code]

  3. Bridging Theory and Algorithm for Domain Adaptation
    Yuchen Zhang, Tianle Liu, Mingsheng Long*, Michael I. Jordan
    International Conference on Machine Learning (ICML), 2019 [PDF] [Appendix] [Code]

  4. Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
    Kaichao You, Ximei Wang, Mingsheng Long*, Michael I. Jordan
    International Conference on Machine Learning (ICML), 2019 [PDF] [Code]

  5. Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers
    Hong Liu, Mingsheng Long*, Jianmin Wang, Michael I. Jordan
    International Conference on Machine Learning (ICML), 2019 [PDF] [Code]

  6. Transferability vs. Discriminability: Batch Spectral Penalization for Adversarial Domain Adaptation
    Xinyang Chen, Sinan Wang, Mingsheng Long*, Jianmin Wang
    International Conference on Machine Learning (ICML), 2019 [PDF] [Code]

  7. Maximum-Margin Hamming Hashing
    Rong Kang, Yue Cao, Mingsheng Long*, Jianmin Wang, Philip S. Yu
    IEEE International Conference on Computer Vision (ICCV), 2019 [PDF] [Code]

  8. Universal Domain Adaptation
    Kaichao You, Mingsheng Long*, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF] [Code]

  9. Separate to Adapt: Open Set Domain Adaptation via Progressive Separation
    Hong Liu, Zhangjie Cao, Mingsheng Long*, Jianmin Wang, Qiang Yang
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF] [Code]

  10. Memory In Memory: A Predictive Neural Network for Learning Higher-Order Non-Stationarity from Spatiotemporal Dynamics
    Yunbo Wang, Jianjin Zhang, Hongyu Zhu, Mingsheng Long*, Jianmin Wang, Philip S. Yu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019 [PDF] [Code]

  11. Eidetic 3D LSTM: A Model for Video Prediction and Beyond
    Yunbo Wang, Lu Jiang, Ming-Hsuan Yang, Li-Jia Li, Mingsheng Long, Li Fei-Fei
    International Conference on Learning Representations (ICLR), 2019 [PDF]

  12. Transferable Attention for Domain Adaptation
    Ximei Wang, Liang Li, Weirui Ye, Mingsheng Long*, Jianmin Wang
    AAAI Conference on Artificial Intelligence (AAAI), 2019 [PDF]

  13. Conditional Adversarial Domain Adaptation
    Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NIPS), 2018 [PDF] [Poster] [Code]

  14. Generalized Zero-Shot Learning with Deep Calibration Network
    Shichen Liu, Mingsheng Long*, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NIPS), 2018 [PDF] [Code]

  15. Partial Adversarial Domain Adaptation
    Zhangjie Cao, Lijia Ma, Mingsheng Long*, Jianmin Wang
    European Conference on Computer Vision (ECCV), 2018 [PDF] [Code]

  16. PredRNN++: Towards A Resolution of the Deep-in-Time Dilemma in Spatiotemporal Predictive Learning
    Yunbo Wang, Zhifeng Gao, Mingsheng Long*, Jianmin Wang, Philip S. Yu
    International Conference on Machine Learning (ICML), 2018 [PDF] [Code]

  17. Partial Transfer Learning with Selective Adversarial Networks
    Zhangjie Cao, Mingsheng Long*, Jianmin Wang, Michael I. Jordan
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2018 [PDF] [Slides] [Code]

  18. Multi-Adversarial Domain Adaptation
    Zhongyi Pei, Zhangjie Cao, Mingsheng Long*, Jianmin Wang
    AAAI Conference on Artificial Intelligence (AAAI), 2018 [PDF] [Code]

  19. PredRNN: Recurrent Neural Networks for Predictive Learning using Spatiotemporal LSTMs
    Yunbo Wang, Mingsheng Long*, Jianmin Wang, Zhifeng Gao, Philip S. Yu
    Neural Information Processing Systems (NIPS), 2017 [PDF]

  20. Learning Multiple Tasks with Multilinear Relationship Networks
    Mingsheng Long, Zhangjie Cao, Jianmin Wang, Philip S. Yu
    Neural Information Processing Systems (NIPS), 2017 [PDF] [Poster] [Code]

  21. HashNet: Deep Learning to Hash by Continuation
    Zhangjie Cao, Mingsheng Long*, Jianmin Wang, Philip S. Yu
    IEEE International Conference on Computer Vision (ICCV), 2017 [PDF] [Code]

  22. Deep Transfer Learning with Joint Adaptation Networks
    Mingsheng Long, Han Zhu, Jianmin Wang, Michael I. Jordan
    International Conference on Machine Learning (ICML), 2017 [PDF] [Slides] [Poster] [Code]

  23. Spatiotemporal Pyramid Network for Video Action Recognition
    Yunbo Wang, Mingsheng Long*, Jianmin Wang, Philip S. Yu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017 [PDF] [Slides] [Code]

  24. Unsupervised Domain Adaptation with Residual Transfer Networks
    Mingsheng Long, Han Zhu, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NIPS), 2016 [PDF] [Poster] [Code]

  25. Deep Hashing Network for Efficient Similarity Retrieval
    Han Zhu, Mingsheng Long*, Jianmin Wang, Yue Cao
    AAAI Conference on Artificial Intelligence (AAAI), 2016 [PDF] [Code]

  26. Learning Transferable Features with Deep Adaptation Networks
    Mingsheng Long, Yue Cao, Jianmin Wang, Michael I. Jordan
    International Conference on Machine Learning (ICML), 2015 [PDF] [Slides] [Poster] [Code] (1000+ Citations)

  27. Transfer Joint Matching for Unsupervised Domain Adaptation
    Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014 [PDF] [Code]

  28. Transfer Feature Learning with Joint Distribution Adaptation
    Mingsheng Long, Jianmin Wang, Guiguang Ding, Jiaguang Sun, Philip S. Yu
    IEEE International Conference on Computer Vision (ICCV), 2013 [PDF] [Code]

  29. Transfer Sparse Coding for Robust Image Representation
    Mingsheng Long, Guiguang Ding, Jianmin Wang, Jiaguang Sun, Philip S. Yu
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2013 [PDF] [Code]

  30. Dual Transfer Learning
    Mingsheng Long, Jianmin Wang, Guiguang Ding, Wei Cheng, Xiang Zhang, Wei Wang
    SIAM International Conference on Data Mining (SDM), 2012 [PDF] (Nominee of Best Paper Award)

Software


Honors and Awards


Professional Activities


Invited Talks

PC Chair

Area Chair

Senior PC Member

PC Member | Reviewer

Research Grants


Teaching


Students


Graduates

Undergraduates