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.|
- Four of my papers are highly cited and ranked top 20 globally in recent 5 years in Google scholar metrics! See here.
- I wrote a popular book 迁移学习导论 to make it easy to learn, understand, and use transfer learning.
- I lead the most popular transfer learning and semi-supervised learning projects on Github: Transfer learning repo and Semi-supervised learning repo
- 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]
- 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]
- 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]
- 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]
NeurIPSFlexmatch: Boosting semi-supervised learning with curriculum pseudo labelingAdvances in Neural Information Processing Systems 2021
CIKMAdarnn: Adaptive learning and forecasting of time seriesProceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM) 2021
ACMMMVisual domain adaptation with manifold embedded distribution alignmentProceedings of the 26th ACM international conference on Multimedia 2018
ICDMBalanced distribution adaptation for transfer learning2017 IEEE international conference on data mining (ICDM) 2017
TKDEUnsupervised deep anomaly detection for multi-sensor time-series signalsIEEE Transactions on Knowledge and Data Engineering (TKDE) 2021