Yang Shu

Assistant Professor
School of Data Science and Engineering
East China Normal University

Email: yshu@dase.ecnu.edu.cn
Previous email: shu-y18@mails.tsinghua.edu.cn (no longer in use)
Mail: Room 109, Geography Building, 3663 North Zhongshan Road, Shanghai
Google Scholar


My research aims at creating strong learning machines that adapt to complex real world. I am working on transfer learning, out-of-distribution (OOD) generalization, domain adaptation and few-shot learning. I am also interested in related topics in machine learning and deep learning, such as foundation models, time series analysis and multi-modal learning.

I am currently an Assistant Professor, Chenhui Scholar, in School of Data Science and Engineering, East China Normal University. I received my Ph.D. degree from School of Software, Tsinghua University, advised by Mingsheng Long. I received my B.S. degree from Department of Automation, Tsinghua University.

Preprints

  1. Transferability in Deep Learning: A Survey
    Junguang Jiang*, Yang Shu*, Jianmin Wang, Mingsheng Long*
    [Paper] [Website]

Publications

  1. Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
    Peng Chen, Yingying Zhang, Yunyao Cheng, Yang Shu*, Yihang Wang, Qingsong Wen, Bin Yang, Chenjuan Guo
    International Conference on Learning Representations (ICLR), 2024 [Paper]

  2. Omni-Training: Bridging Pre-Training and Meta-Training for Few-Shot Learning
    Yang Shu, Zhangjie Cao, Jinghan Gao, Jianmin Wang, Philip S. Yu, Mingsheng Long*
    IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 2023 [Paper]

  3. CLIPood: Generalizing CLIP to Out-of-Distributions
    Yang Shu*, Xingzhuo Guo*, Jialong Wu, Ximei Wang, Jianmin Wang, Mingsheng Long*
    International Conference on Machine Learning (ICML), 2023 [Paper] [Code]

  4. Hub-Pathway: Transfer Learning from A Hub of Pre-trained Models
    Yang Shu, Zhangjie Cao, Ziyang Zhang, Jianmin Wang, Mingsheng Long*
    Neural Information Processing Systems (NeurIPS), 2022 [Paper]

  5. 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 [Paper] [Code]

  6. Open Domain Generalization with Domain-Augmented Meta-Learning
    Yang Shu*, Zhangjie Cao*, Chenyu Wang, Jianmin Wang, Mingsheng Long*
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [Paper] [Code]

  7. Transferable Curriculum for Weakly-Supervised Domain Adaptation
    Yang Shu, Zhangjie Cao, Mingsheng Long*, Jianmin Wang
    AAAI Conference on Artificial Intelligence (AAAI), 2019 [Paper] [Code]

Academic Services

PC Member
  • International Conference on Learning Representations (ICLR), 2024
  • Neural Information Processing Systems (NeurIPS), 2022, 2023
  • European Conference on Computer Vision (ECCV), 2022, 2024
  • International Conference on Machine Learning (ICML), 2022, 2023, 2024
  • IEEE International Conference on Computer Vision (ICCV), 2021, 2023
  • IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021, 2022, 2023
  • International Joint Conference on Artificial Intelligence (IJCAI), 2020
Reviewer
  • IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI)
  • IEEE Transactions on Knowledge and Data Engineering (TKDE)
  • International Journal of Computer Vision (IJCV)
  • Artificial Intelligence Journal (AIJ)
  • Information Sciences
  • IEEE Transactions on Circuits and Systems for Video Technology (TCSVT)