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, China

Reminder: There are no opening positions for PhD or Master students in Class 2022. [Instructions]

Biography


My research spans machine learning theories and algorithms, with special interests in transfer learning, deep learning, and scientific learning. My research is persistently dedicated to enabling adaptive machine learning in open, dynamic and non-stationary world, including representation learning, predictive learning, transfer learning, domain adaptation, multitask learning and learning to learn.

I am leading the Machine Learning Group. Our team is interested in developing foundational theories, effective algorithms, and reliable systems of machine learning to enable systematic generalization in data representation, inference, and decision making. We focus on industrial applications of AI and data science, including text, sequence, image, video, and scientific data analysis and understanding.

My Quote

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

Research Interests


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. LogME: Practical Assessment of Pre-trained Models for Transfer Learning
    Kaichao You, Yong Liu, Jianmin Wang, Mingsheng Long* [arXiv 2021]

  2. Self-Tuning for Data-Efficient Deep Learning
    Ximei Wang, Jinghan Gao, Jianmin Wang, Mingsheng Long* [arXiv 2021]

  3. Cycle Self-Training for Domain Adaptation
    Hong Liu, Jianmin Wang, Mingsheng Long* [arXiv 2021]

  4. On Localized Discrepancy for Domain Adaptation
    Yuchen Zhang, Mingsheng Long*, Jianmin Wang, Michael I. Jordan [arXiv 2020]

  5. Bi-tuning of Pre-trained Representations
    Jincheng Zhong, Ximei Wang, Zhi Kou, Jianmin Wang, Mingsheng Long* [arXiv 2020]

  6. Adversarial Pyramid Network for Video Domain Generalization
    Zhiyu Yao, Yunbo Wang, Xingqiang Du, Mingsheng Long*, Jianmin Wang [arXiv 2020]

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. 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]

Conference Proceedings

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

  2. Conditional Adversarial Domain Adaptation
    Mingsheng Long, Zhangjie Cao, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NeurIPS), 2018 [PDF] [Poster] [Code] (500+ Citations)
    PaperDigest Most Influential Papers

  3. 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]

  4. 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]

  5. 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]

  6. 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] (800+ Citations)

  7. 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] (700+ Citations)

  8. 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] (2000+ Citations)
    PaperDigest Most Influential Papers

Invited Talks


Software


Awards


Professional Services


PC Chair

Area Chair

Guest Editor

Senior PC Member

PC Member | Reviewer

Research Grants


Teaching


Students


PhDs

Masters

Undergraduates