Jindong Wang

Senior 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 | DBLP | Github || Twitter | Zhihu | Wechat | Bilibili || CV CV (Chinese)

I’m currently a Senior Researcher at Microsoft Research Asia (MSRA), in a group managed by Xing Xie. 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 won the best paper awards in ICCSE 2018 and FTL-IJCAI 2019. In 2021, I published the textbook Introduction to Transfer Learning, a hands-on introduction to transfer learning. In 2022, I was selected as one of the 2022 AI 2000 Most Influential Scholars by AMiner between 2012-2021 (ranked 49/2000). Four of my first-author papers are ranked by Google Scholar as highly-cited papers. I gave tutorials at IJCAI’22.

Research interest: robust machine learning, out-of-distribution / domain generalization, transfer learning, semi-supervised learning, federated learning, and related applications such as activity recognition and computer vision. These days, I’m particularly interested in Large Language Models (LLMs) robustness. See this page for more details. Interested in internship or collaboration? Contact me.

Announcement: I’m experimenting a new form of research collaboration. You can click here if you are interested!

News

May 17, 2023	Two papers are accepted by KDD 2023.
May 4, 2023	The large model for large model evaluation “PandaLM” is released on Github! [PandaLM]
May 3, 2023	Our paper “GLUE-X: Evaluating Natural Language Understanding Models from an Out-of-distribution Generalization Perspective” is accepted by ACL 2023 findings! [paper]
May 1, 2023	We will give a tutorial on KDD 2023 named “Trustworthy machine learning: generalization, robustness, and interpretability”!
Apr 17, 2023	Two papers (FedCLIP and ChatGPT robustness) are accepted by ICLR 2023 workshop on robust large models! [Papers]
Apr 5, 2023	The English version of 迁移学习导论 is published online: [Springer]

Highlights

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 Introduction to Transfer Learning 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, Semi-supervised learning repo, and Personalized federated learning repo.
I was selected into the list of 2022 AI 2000 Most Influential Scholars by AMiner in recognition of my contributions in the field of multimedia between 2012-2021 (ranked 49/2000)

Selected publications

Domain-Specific Risk Minimization for Out-of-Distribution Generalization

Yi-Fan Zhang, Jindong Wang^# , Jian Liang, Zhang Zhang, Baosheng Yu, Liang Wang, Dacheng Tao, and Xing Xie

The 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) 2023 | [ arXiv Code Zhihu ]
Out-of-distribution Representation Learning for Time Series Classification

Wang Lu, Jindong Wang^# , Xinwei Sun, Yiqiang Chen, and Xing Xie

International Conference on Learning Representations (ICLR) 2023 | [ arXiv Code Website Zhihu ]
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

Yidong Wang, Hao Chen, Qiang Heng, Wenxin Hou, Yue Fan, Zhen Wu, Jindong Wang^# , Marios Savvides, Takahiro Shinozaki, Bhiksha Raj, Bernt Schiele, and Xing Xie

International Conference on Learning Representations (ICLR) 2023 | [ arXiv Code Website Zhihu ]
Generalizing to Unseen Domains: A Survey on Domain Generalization

Jindong Wang , Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin, Wang Lu, Yiqiang Chen, Wenjun Zeng, and Philip S. Yu

IEEE Transactions on Knowledge and Data Engineering (TKDE) 2022 | [ arXiv PDF Code Slides Website ]
```
@article{wang2022generalizing,
  title = {Generalizing to Unseen Domains: A Survey on Domain Generalization},
  author = {Wang, Jindong and Lan, Cuiling and Liu, Chang and Ouyang, Yidong and Qin, Tao and Lu, Wang and Chen, Yiqiang and Zeng, Wenjun and Yu, Philip S.},
  journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
  year = {2022},
  bibtex_show = {true},
  abbr = {TKDE},
  arxiv = {https://arxiv.org/abs/2103.03097},
  code = {https://github.com/jindongwang/transferlearning/tree/master/code/DeepDG},
  slides = {DGtutorial_ijcai22.pdf},
  selected = {true},
  pdf = {DG_survey_TKDE22.pdf},
  website = {https://dgresearch.github.io/}
}
```
Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition

Wang Lu, Jindong Wang^# , Yiqiang Chen, Sinno Pan, Chunyu Hu, and Xin Qin

Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies (IMWUT, i.e., UbiComp) 2022 | [ arXiv PDF ]
```
@article{lu2022semantic,
  title = {Semantic-Discriminative Mixup for Generalizable Sensor-based Cross-domain Activity Recognition},
  author = {Lu, Wang and Wang, Jindong and Chen, Yiqiang and Pan, Sinno and Hu, Chunyu and Qin, Xin},
  journal = {Proceedings of the ACM on Interactive, Mobile, Wearable, and Ubiquitous Technologies (IMWUT, i.e., UbiComp)},
  year = {2022},
  abbr = {IMWUT},
  bibtex_show = {true},
  corr = {true},
  selected = {true},
  arxiv = {http://arxiv.org/abs/2206.06629},
  pdf = {imwut22-sdmix.pdf}
}
```
Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection

Yuxin Zhang, Jindong Wang^# , Yiqiang Chen, Han Yu, and Tao Qin

IEEE Transactions on Knowledge and Data Engineering (TKDE) 2022 | [ arXiv PDF Code ]
```
@article{zhang2022adaptive,
  title = {Adaptive Memory Networks with Self-supervised Learning for Unsupervised Anomaly Detection},
  author = {Zhang, Yuxin and Wang, Jindong and Chen, Yiqiang and Yu, Han and Qin, Tao},
  journal = {IEEE Transactions on Knowledge and Data Engineering (TKDE)},
  year = {2022},
  abbr = {TKDE},
  bibtex_show = {true},
  corr = {true},
  selected = {true},
  arxiv = {https://arxiv.org/abs/2201.00464},
  pdf = {tkde22_amsl.pdf},
  code = {https://github.com/zhangyuxin621/AMSL}
}
```
ReMoS: Reducing Defect Inheritance in Transfer Learning via Relevant Model Slicing

Ziqi Zhang, Yuanchun Li, Jindong Wang , Bingyan Liu, Ding Li, Xiangqun Chen, Yao Guo, and Yunxin Liu

44th International Conference on Software Engineering (ICSE) 2022 | [ PDF Code Video Zhihu ]
```
@inproceedings{zhang2022remos,
  title = {ReMoS: Reducing Defect Inheritance in Transfer Learning via Relevant Model Slicing},
  author = {Zhang, Ziqi and Li, Yuanchun and Wang, Jindong and Liu, Bingyan and Li, Ding and Chen, Xiangqun and Guo, Yao and Liu, Yunxin},
  booktitle = {44th International Conference on Software Engineering (ICSE)},
  year = {2022},
  bibtex_show = {true},
  abbr = {ICSE},
  pdf = {icse22-remos.pdf},
  code = {https://github.com/jindongwang/transferlearning/tree/master/code/deep/ReMoS},
  zhihu = {https://zhuanlan.zhihu.com/p/446453487},
  video = {https://www.bilibili.com/video/BV1mi4y1C7bP},
  selected = {true}
}
```
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 (NeurIPS) 2021 | [ arXiv PDF Code Slides Video Zhihu ]
```
@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}
}
```
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 | [ arXiv PDF Code ]
```
@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}
}
```
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 | [ PDF Supp Code Poster ]

(400+ citations; 2nd most cited paper in MM’18)
```
@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 = {400+ 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 | [ HTML PDF Code ]

(400+ citations; most cited paper in ICDM’17)
```
@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 = {400+ citations; most cited paper in ICDM'17}
}
```