Jindong Wang

Researcher, Microsoft Research Asia
Building 2, No. 5 Danling Street, Haidian District, Beijing, China
jindongwang [at] outlook.com, jindong.wang [at] microsoft.com
Google scholar | Github | DBLP | Zhihu | Weibo | Wechat | Bilibili

I’m currently a researcher at Microsoft Research Asia (MSRA). Before joining MSRA, I obtained my Ph.D. from Institute of Computing Technology, Chinese Academy of Sciences in June, 2019. My doctoral thesis was awarded the excellent Ph.D. thesis of Chinese Academy of Sciences. In 2018/04–2018/08, I was a visitor of Prof. Qiang Yang’s group at Hong Kong University of Science and Technology (HKUST). My work on transfer learning has won the best paper awards in ICCSE 2018 and FTL-IJCAI 2019. In 2021, I published the textbook 迁移学习导论, a hands-on introduction to transfer learning. Never stop looking for highly self-motivated students for internship or collaboration.

Research interest: transfer learning, meta-learning, out-of-distribution generalization, semi-supervised learning, and related applications.


Dec 24, 2021 Our paper Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection has been accepted by IEEE TKDE! [arXiv]
Dec 14, 2021 Our paper Exploiting Adapters for Cross-lingual Low-resource Speech Recognition is accepted by IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)! [arXiv] [code]
Dec 3, 2021 Our paper ReMoS: Reducing Defect Inheritance in Transfer Learning via Relevant Model Slicing is accepted by ICSE 2022!
Oct 20, 2021 Four of my papers are ranked top 20 in recent 5 years in Google scholar metrics! See here.


  1. Four of my papers are highly cited and ranked top 20 globally in recent 5 years in Google scholar metrics! See here.
  2. I wrote a popular book 迁移学习导论 to make it easy to learn, understand, and use transfer learning.
  3. I lead the most popular transfer learning and semi-supervised learning projects on Github: Transfer learning repo Transfer learning repo and Semi-supervised learning repo SSL repo


  1. Yidong Wang, Bowen Zhang, Wenxin Hou, Zhen Wu, Jindong Wang#, Takahiro Shinozaki. Margin Calibration for Long-Tailed Visual Recognition. arXiv preprint arXiv:2112.07225. [arXiv]
  2. Yiqiang Chen, Wang Lu, Jindong Wang, Xin Qin, and Tao Qin. Federated Learning with Adaptive Batchnorm for Personalized Healthcare. arXiv preprint arXiv:2112.00734. [arXiv]
  3. Jindong Wang, Wenjie Feng, Chang Liu, Chaohui Yu, Mingxuan Du, Renjun Xu, Tao Qin, and Tie-Yan Liu. Learning Invariant Representations across Domains and Tasks. arXiv preprint arXiv:2103.05114. [arXiv]
  4. Chaohui Yu, Jindong Wang#, Chang Liu, Tao Qin, Renjun Xu, Wenjie Feng, Yiqiang Chen, and Tie-Yan Liu. Learning to match distributions for domain adaptation. arXiv preprint arXiv:2007.10791. [arXiv]

Selected publications

  1. NeurIPS
    Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling
    Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang# , Manabu Okumura, and Takahiro Shinozaki
    Advances in Neural Information Processing Systems 2021
  2. CIKM
    Adarnn: Adaptive learning and forecasting of time series
    Yuntao Du, Jindong Wang# , Wenjie Feng, Sinno Pan, Tao Qin, Renjun Xu, and Chongjun Wang
    Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM) 2021
  3. ACMMM
    Visual domain adaptation with manifold embedded distribution alignment
    Jindong Wang , Wenjie Feng, Yiqiang Chen, Han Yu, Meiyu Huang, and Philip S Yu
    Proceedings of the 26th ACM international conference on Multimedia 2018
  4. ICDM
    Balanced distribution adaptation for transfer learning
    Jindong Wang , Yiqiang Chen, Shuji Hao, Wenjie Feng, and Zhiqi Shen
    2017 IEEE international conference on data mining (ICDM) 2017
  1. TKDE
    Unsupervised deep anomaly detection for multi-sensor time-series signals
    Yuxin Zhang, Yiqiang Chen, Jindong Wang# , and Zhiwen Pan
    IEEE Transactions on Knowledge and Data Engineering (TKDE) 2021
Hit Counter