Mingsheng Long


Mingsheng Long

Associate Professor, PhD Supervisor

Machine Learning Group
School of Software
Tsinghua University

longmingsheng@gmail.com
mingsheng@tsinghua.edu.cn
Room 11-413, East Main Building, Tsinghua University, Beijing 100084, China

[Publications] [Google Scholar] [THUML @ Github] [Subscription @ WeChat] [Instruction to Applicants]

Biography


My research spans theories, algorithms, and applications of machine learning, with persistent dedication to enable adaptive machine learning in the open, dynamic and non-stationary world. My current research is to promote advances in transfer, adaptation, and data-efficient learning, foundation deep models, learning with spatiotemporal and scientific knowledge.

Our Machine Learning Group is interested in developing machine learning technology for systematic generalization in representation, inference, and decision making with good trade-off between accuracy, efficiency, and stability. We focus on industrial applications of AI and data science, including analysis and understanding of vision, language, IoT, and science data.

My Quote

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

Research Interests


Education


Research Experience


Recent News


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

(* Corresponding Author)


Thesis

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

Journal Articles

  1. VideoDG: Generalizing Temporal Relations in Videos to Novel Domains
    Zhiyu Yao, Yunbo Wang, Jianmin Wang, Philip S. Yu, Mingsheng Long*
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 99(Preprint), 2021 [arXiv] [Code]

  2. 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] [Code]

Conference Proceedings

  1. LogME: Practical Assessment of Pre-trained Models for Transfer Learning
    Kaichao You, Yong Liu, Jianmin Wang, Mingsheng Long*
    International Conference on Machine Learning (ICML), 2021 [PDF] [Appendix] [Code]

  2. Zoo-Tuning: Adaptive Transfer from A Zoo of Models
    Yang Shu, Zhi Kou, Zhangjie Cao, Jianmin Wang, Mingsheng Long*
    International Conference on Machine Learning (ICML), 2021 [PDF] [Appendix] [Code]

  3. Self-Tuning for Data-Efficient Deep Learning
    Ximei Wang, Jinghan Gao, Jianmin Wang, Mingsheng Long*
    International Conference on Machine Learning (ICML), 2021 [PDF] [Appendix] [Code]

  4. Representation Subspace Distance for Domain Adaptation Regression
    Xinyang Chen, Sinan Wang, Jianmin Wang, Mingsheng Long*
    International Conference on Machine Learning (ICML), 2021 [PDF] [Appendix] [Code]

  5. Transferable Calibration with Lower Bias and Variance in Domain Adaptation
    Ximei Wang, Mingsheng Long*, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NeurIPS), 2020 [PDF] [Appendix] [Code]

  6. Co-Tuning for Transfer Learning
    Kaichao You, Zhi Kou, Mingsheng Long*, Jianmin Wang
    Neural Information Processing Systems (NeurIPS), 2020 [PDF] [Code]

  7. Stochastic Normalization
    Zhi Kou, Kaichao You, Mingsheng Long*, Jianmin Wang
    Neural Information Processing Systems (NeurIPS), 2020 [PDF] [Code]

  8. Learning to Adapt to Evolving Domains
    Hong Liu, Mingsheng Long*, Jianmin Wang, Yu Wang
    Neural Information Processing Systems (NeurIPS), 2020 [PDF] [Code]

  9. Unsupervised Transfer Learning for Spatiotemporal Predictive Networks
    Zhiyu Yao, Yunbo Wang, Mingsheng Long*, Jianmin Wang
    International Conference on Machine Learning (ICML), 2020 [PDF] [Code]

  10. 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 (NeurIPS), 2019 [PDF] [Code]

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

  12. 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] (Long Oral)

  13. 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]

  14. 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] (Long Oral)

  15. 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]

  16. Conditional Adversarial Domain Adaptation
    Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NeurIPS), 2018 [PDF] [Poster] [Code]
    PaperDigest Most Influential Papers

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

  18. 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]

  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 (NeurIPS), 2017 [PDF] [Code]

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

  21. 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] (Long Oral)
    PaperDigest Most Influential Papers

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

  23. 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] (Long Oral)
    PaperDigest Most Influential Papers

Invited Talks


Software


Awards


Professional Services


PC Chair

Area Chair

Associate Editor

Guest Editor

(Senior) PC Member | Reviewer

Research Grants


Teaching


Students


PhDs

Masters

Undergraduates