Dr. Jindong Wang is currently a Senior Researcher at Microsoft Research Asia. He obtained his Ph.D from Institute of Computing Technology, Chinese Academy of Sciences in 2019. In 2018, he visited Prof. Qiang Yangâs group at Hong Kong University of Science and Technology. His research interest includes robust machine learning, transfer learning, semi-supervised learning, and federated learning. His recent interest is large language models. He has published over 50 papers with 10000+ citations at leading conferences and journals such as ICLR, NeurIPS, TPAMI, IJCV etc. His research is reported by Forbes and other international media. He has several Google scholar highly cited papers, Huggingface featured papers, and paperdigest most influential papers. He received the best paper award at ICCSEâ18 and IJCAIâ19 federated learning workshop and the prestigous excellent Ph.D thesis award (only 1 at ICT each year). In 2023, he was selected by Stanford University as one of the Worldâs 2% Scientists and one of the AI Most Influential Scholars by AMiner. He serves as the associate editor of IEEE Transactions on Neural Networks and Learning Systems (TNNLS), guest editor for ACM Transactions on Intelligent Systems and Technology (TIST), area chair for NeurIPS, KDD, and ACMMM, senior program committee member of IJCAI and AAAI, and reviewers for top conferences and journals like ICML, NeurIPS, ICLR, CVPR, TPAMI, AIJ etc. He leads several impactful open-source projects, including transferlearning, PromptBench, torchSSL, USB, personalizedFL, and robustlearn, which received over 16K stars on Github. He published a textbook Introduction to Transfer Learning to help starters quickly learn transfer learning. He gave tutorials at IJCAIâ22, WSDMâ23, KDDâ23, and AAAIâ24.
Research interest: (See this page for more details)
Machine learning: robust machine learning, OOD / domain generalization, transfer learning, semi-supervised learning, federated learning, and related applications.
Interested in internship or collaboration? Contact me. Iâm experimenting a new form of research collaboration. You can click here if you are interested!
News
Jul 2, 2024
Our paper âSpecFormer: Guarding Vision Transformer Robustness via Maximum Singular Value Penalizationâ is accepted by ECCV 2024! [paper]
May 16, 2024
We have 4 collaborative papers accepted by ACL 2024 (2 main, 2 findings). Congrats to authors!
May 14, 2024
Invited to be an area chair for NeurIPS 2024 main track.
May 7, 2024
The PromptBench framework has been accepted by JMLR open-source track! NegativePrompt (variation of EmotionPrompt) is accepted by IJCAI 2024 main track!
May 2, 2024
We have 8 papers accepted by ICML 2024 (4 from my team and 4 collaborative work). Congrats!
Jan 20, 2024
I was invited to be an Area Chair for ACM Multimedia 2024.
Highlights
6 of my papers are highly cited and ranked top 20 globally in recent 5 years in Google scholar metrics. See here. I also have 6 papers featured by Hugging Face.
@article{zhang2021flexmatch,title={Flexmatch: Boosting semi-supervised learning with curriculum pseudo labeling},author={Zhang, Bowen and Wang, Yidong and Hou, Wenxin and Wu, Hao and Wang, Jindong and Okumura, Manabu and Shinozaki, Takahiro},journal={Advances in Neural Information Processing Systems (NeurIPS)},volume={34},year={2021},bibtex_show={true},corr={true},abbr={NeurIPS},arxiv={https://arxiv.org/abs/2110.08263},pdf={http://jd92.wang/assets/files/flexmatch_nips21.pdf},code={https://github.com/TorchSSL/TorchSSL},zhihu={https://zhuanlan.zhihu.com/p/422930830},video={https://www.youtube.com/watch?v=aYuUwyZl_WY},slides={https://www.jianguoyun.com/p/DXeFVg8QjKnsBRibj54E},selected={true},special={500+ citations}}
Adarnn: Adaptive learning and forecasting of time series
Yuntao Du,
Jindong Wang#
,
Wenjie Feng,
Sinno Pan,
Tao Qin,
Renjun Xu,
and Chongjun Wang
The 30th ACM International Conference on Information & Knowledge Management (CIKM)
2021
| [
arXivPDFCode
]
(Paperdigest most influencial CIKM paper)
@inproceedings{du2021adarnn,title={Adarnn: Adaptive learning and forecasting of time series},author={Du, Yuntao and Wang, Jindong and Feng, Wenjie and Pan, Sinno and Qin, Tao and Xu, Renjun and Wang, Chongjun},booktitle={The 30th ACM International Conference on Information \& Knowledge Management (CIKM)},pages={402--411},year={2021},bibtex_show={true},abbr={CIKM},corr={true},selected={true},arxiv={https://arxiv.org/abs/2108.04443},code={https://github.com/jindongwang/transferlearning/tree/master/code/deep/adarnn},pdf={cikm21-adarnn.pdf},special={Paperdigest most influencial CIKM paper}}
Visual domain adaptation with manifold embedded distribution alignment
Jindong Wang
,
Wenjie Feng,
Yiqiang Chen,
Han Yu,
Meiyu Huang,
and Philip S Yu
The 26th ACM international conference on Multimedia
2018
| [
PDFSuppCodePoster
]
(500+ citations; 2nd most cited paper in MMâ18)
@inproceedings{wang2018visual,title={Visual domain adaptation with manifold embedded distribution alignment},author={Wang, Jindong and Feng, Wenjie and Chen, Yiqiang and Yu, Han and Huang, Meiyu and Yu, Philip S},booktitle={The 26th ACM international conference on Multimedia},pages={402--410},year={2018},bibtex_show={true},abbr={ACMMM},code={https://github.com/jindongwang/transferlearning/tree/master/code/traditional/MEDA},pdf={a11_mm18.pdf},supp={https://www.jianguoyun.com/p/DRuWOFkQjKnsBRjkr2E},poster={poster_mm18.pdf},selected={true},special={500+ citations; 2nd most cited paper in MM'18}}
Balanced distribution adaptation for transfer learning
Jindong Wang
,
Yiqiang Chen,
Shuji Hao,
Wenjie Feng,
and Zhiqi Shen
IEEE international conference on data mining (ICDM)
2017
| [
HTMLPDFCode
]
(500+ citations; most cited paper in ICDMâ17)
@inproceedings{wang2017balanced,title={Balanced distribution adaptation for transfer learning},author={Wang, Jindong and Chen, Yiqiang and Hao, Shuji and Feng, Wenjie and Shen, Zhiqi},booktitle={IEEE international conference on data mining (ICDM)},pages={1129--1134},year={2017},organization={IEEE},bibtex_show={true},abbr={ICDM},code={https://github.com/jindongwang/transferlearning/tree/master/code/BDA},pdf={a08_icdm17.pdf},html={http://ieeexplore.ieee.org/document/8215613/?part=1},selected={true},special={500+ citations; most cited paper in ICDM'17}}