Jindong Wang (王晋东)
Researcher
Machine Learning Group, Microsoft Research Asia (MSRA)

Google Scholar | DBLP | Github Zhihu Weibo | Wechat public account

Contact: Building 2, No. 5 DanLing Street, Haidian District, Beijing, China.
jindong.wang (at) microsoft.com, jindongwang (at) outlook.com
News
  • 2021-09: Two of our papers on causality for generalization and semi-supervised learning are accepted by NeurIPS 2021!
  • 2021-08: Our paper AdaRNN: Adaptive Learning and Forecasting of Time Series is accepted by CIKM 2021! [ArXiv] [Code]
  • 2021-07: Our paper Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals is accepted by IEEE TKDE. [ArXiv]
  • 2021-07: Our paper FedHealth 2 for federated transfer learning is accepted by IJCAI-21 workshop on federated learning. [ArXiv]
  • 2021-05: Our paper Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching was accepted by Interspeech-21!
  • 2021-05: Our new Chinese textbook 《迁移学习导论》 is officially released! [Zhihu] [Buy] [Homepage]
  • 2021-05: Our paper Cross-domain Activity Recognition via Substructural Optimal Transport was accepted by Neurocomputing! [Zhihu]
  • 2021-04-16: Our paper Generaling to unseen domains was accepted by IJCAI 2021!
  • Internship: Looking for highly-motivated students to collaborate or for internship. (The new internship period starts in 2021/06.) Please send me your CVs if you're interested. Keep an eye on this article for more detail.
  • Call for papers: Advances in Transfer Learning: Theory, Algorithms, and Applications
Bio
Dr. Jindong Wang is currently a researcher at machine learning group, Microsoft Research Asia (MSRA). Before joining MSRA, he obtained the Ph.D. from Institute of Computing Technology, Chinese Academy of Sciences in June, 2019. His doctoral thesis Adaptive transfer learning methods in ubiquitous computing was awarded the excellent Ph.D. thesis of Chinese Academy of Sciences. In 2018/04--2018/08, he was a visitor of Prof. Qiang Yang's group at Hong Kong University of Science and Technology (HKUST). His work on transfer learning has won several best paper awards in ICCSE 2018 and FTL-IJCAI 2019. In 2021, he published his textbook 迁移学习导论, an introduction to transfer learning. His research interest is mainly about adaptation and generalization problems, including but not limited to: transfer learning, few-shot learning, meta-learning, adaptive learning, and related applications.
[Research] [Education] [Publications] [Talks] [Projects] [Awards & Service]

Research Experience
Publications

Technical reports

  1. Exploiting Adapters for Cross-lingual Low-resource Speech Recognition. [ArXiv] [Code]
    Wenxin Hou, Han Zhu, Yidong Wang, Jindong Wang, Tao Qin, Renjun Xu, Takahiro Shinozaki.
    Preprint.
  2. Learning Invariant Representations across Domains and Tasks. [ArXiv]
    Jindong Wang, Wenjie Feng, Chang Liu, Chaohui Yu, Mingxuan Du, Renjun Xu, Tao Qin, Tie-Yan Liu.
    Preprint.
  3. Learning to Match Distributions for Domain Adaptation. [ArXiv] [Code]
    Chaohui Yu*, Jindong Wang*, Chang Liu, Tao Qin, Renjun Xu, Wenjie Feng, Yiqiang Chen, Tie-Yan Liu.
    Preprint.

Book

  1. 迁移学习导论. [Homepage] [Zhihu] [Buy]
    Jindong Wang, Yiqiang Chen.
  2. 迁移学习简明手册 (First manual in transfer learning). [Link] [PDF] [Github]
    Jindong Wang.
    Transfer Learning Tutorial 2018

Conference papers

  1. FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling. [arXiv] [PDF] [Code] [Zhihu]
    Bowen Zhang, Yidong Wang, Wenxin Hou, Hao Wu, Jindong Wang*, Manabu Okumura, Takahiro Shinozaki. (*denotes corresponding author)
    To appear at Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS-21).
  2. Learning Causal Semantic Representation for Out-of-Distribution Prediction. [ArXiv]
    Chang Liu, Xinwei Sun, Jindong Wang, Haoyue Tang, Tao Li, Tao Qin, Wei Chen, Tie-Yan Liu.
    To appear at Thirty-Fifth Conference on Neural Information Processing Systems (NeurIPS-21).
  3. AdaRNN: Adaptive Learning and Forecasting of Time Series. [ArXiv] [Code]
    Yuntao Du, Jindong Wang*, Wenjie Feng, Sinno Pan, Tao Qin, Renjun Xu, Chongjun Wang. (* denotes corresponding author)
    In 30th ACM International Conference on Information and Knowledge Management (CIKM-21).
  4. Cross-domain Speech Recognition with Unsupervised Character-level Distribution Matching. [PDF] [ArXiv] [Code]
    Wenxin Hou, Jindong Wang, Xu Tan, Tao Qin, Takahiro Shinozaki.
    In Interspeech 2021.
  5. Generalizing to Unseen Domains: A Survey on Domain Generalization. [ArXiv] [Code] [PPT]
    Jindong Wang, Cuiling Lan, Chang Liu, Yidong Ouyang, Tao Qin.
    In Proceedings of International Joint Conference on Artificial Intelligence 2021 (IJCAI-21). (Full paper)
  6. MixSpeech: Data Augmentation for Low-resource Automatic Speech Recognition. [Arxiv]
    Linghui Meng, Jin Xu, Xu Tan, Jindong Wang, Tao Qin, Bo Xu.
    In Proceedings of IEEE International Conference on Acoustics, Speech and Signal Processing 2021 (ICASSP-21). (Full paper)
  7. Joint Partial Optimal Transport for Open Set Domain Adaptation. [PDF] [Link]
    Renjun Xu, Pelen Liu, Ying Zhang, Fang Cai, Jindong Wang, et al.
    In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI-20). (Full paper)
  8. Reliable Weighted Optimal Transport for Unsupervised Domain Adaptation. [PDF] [Link]
    Pelen Liu, Renjun Xu, Liyan Wang, Chao Chen, Jindong Wang.
    In Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR-20) Virtual. Jun. 14-19, 2020. Pages 4394-4403. (Full paper, AC rate: 22%)
  9. Cross-dataset Activity Recognition via Adaptive Spatial-temporal Transfer Learning. [PDF] [Link]
    Xin Qin, Yiqiang Chen, Jindong Wang, Chaohui Yu.
    To appear in ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp-20).
  10. Transfer Learning with Dynamic Adversarial Adaptation Network. [PDF] [Code]
    Chaohui Yu*, Jindong Wang*, Yiqiang Chen, Meiyu Huang. (* denotes equal contribution)
    In Proceedings of IEEE International Conference on Data Mining (ICDM-19). Beijing, China. Nov. 8-11, 2019. Pages 778-786. (Full Paper, AC rate: 9.08%)
  11. DrowsyDet: A Mobile Application for Real-Time Driver Drowsiness Detection.
    Chaohui Yu, Xin Qin, Yiqiang Chen, Jindong Wang, Chenchen Fan.
    In Proceedings of IEEE International Conference on Ubiquitous Intelligence and Computing (UIC-19). Leicester, UK. Aug. 19-23, 2019. Pages 1-8. (Full paper)
  12. Easy Transfer Learning By Exploiting Intra-domain Structures. [PDF] [Code]
    Jindong Wang, Yiqiang Chen, Han Yu, Meiyu Huang, Qiang Yang.
    In Proceedings of IEEE International Conference on Multimedia and Expo (ICME-19). Shanghai, China. Jul. 8-12, 2019. Pages 1-6. (Full paper)
  13. Accelerating Deep Unsupervised Domain Adaptation with Transfer Channel Prunning. [PDF] [Code]
    Chaohui Yu, Jindong Wang, Yiqiang Chen, Zijing Wu.
    In Proceedings of International Joint Conference on Neural Networks (IJCNN-19). Budapest, Hungary. July 14-19, 2019. Pages 1-8. (Full paper, Oral)
  14. Visual Domain Adaptation with Manifold Embedded Distribution Alignment. [PDF] [Code] [Supplementary] [Poster]
    Jindong Wang, Wenjie Feng, Yiqiang Chen, Han Yu, Meiyu Huang, Philip S. Yu.
    In Proceedings of ACM International Conference on Multimedia (ACMMM-18). Seoul, Korea. Oct. 22-26, 2018. Pages 402-410. (Full paper, Oral, Top 10 papers)
  15. Deep Transfer Learning for Cross-domain Activity Recognition. [PDF] [Link]
    Jindong Wang, Vincent W. Zheng, Yiqiang Chen, Meiyu Huang.
    In Proceedings of The 3rd International Conference on Crowd Science and Engineering (ICCSE-18). Singapore. Jul. 31-Aug. 2, 2018. Pages 1-8. (Best Paper)
  16. Stratified Transfer Learning for Cross-domain Activity Recognition. [PDF] [Code]
    Jindong Wang, Yiqiang Chen, Lisha Hu, Xiaohui Peng, Philip S. Yu.
    In Proceedings of IEEE International Conference on Pervasive Computing and Communications (PerCom-18). Athens, Greece. Mar. 19-23, 2018. Pages 1-10. (Full paper)
  17. Balanced Distribution Adaptation for Transfer Learning. [Link] [PDF] [Code]
    Jindong Wang, Yiqiang Chen, Shuji Hao, Wenjie Feng, Zhiqi Shen.
    In Proceedings of IEEE International Conference on Data Mining (ICDM-17). New Orleans, USA. Nov. 18-21, 2017. Pages 1129-1134. (Short paper)
  18. OCEAN: A New Opportunistic Computing Model for Wearable Activity Recognition. [PDF] [Link]
    Yiqiang Chen, Yang Gu, Xinlong Jiang, Jindong Wang.
    In Proceedings of ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp-16). Heidelberg, Germany. Sep. 12-16, 2016.
  19. Less Annotation on Personalized Activity Recognition Using Context Data. [PDF] [Link]
    Lisha Hu, Yiqiang Chen, Shuangquan Wang, Jindong Wang, Jianfei Shen, Xinlong Jiang, Zhiqi Shen.
    In Proceedings of the 13th IEEE International Conference on Ubiquitous Intelligence and Computing (UIC-16). Toulouse, France. Jul. 18-21, 2016. Pages 327-332.
  20. A Study of Players' Experiences during Brain Games Play. [PDF] [Link]
    Faizan Ahmad, Yiqiang Chen, Shuangquan Wang, Zhenyu Chen, Jianfei Shen, Lisha Hu, Jindong Wang.
    In Proceedings the 14th Pacific Rim International Conference on Artificial Intelligence (PRICAI-16). Phuket, Thailand. Aug. 22-26, 2016. (Full paper)

Journal articles

  1. Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals. [ArXiv] [Zhihu]
    Yuxin Zhang, Yiqiang Chen, Jindong Wang*, Zhiwen Pan. (* denotes corresponding author)
    To appear in IEEE Transactions on Knowledge and Data Engineering (IEEE TKDE) 2021.
  2. Cross-domain Activity Recognition via Substructural Optimal Transport. [ArXiv] [Link] [Zhihu]
    Wang Lu, Yiqiang Chen, Jindong Wang, Xin Qin.
    To appear in Neurocomputing 2021.
  3. Deep Subdomain Adaptation Network for Image Classification. [PDF] [Link] [Code]
    Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Guolin Ke, Jingwu Chen, Jiang Bian, Hui Xiong, Qing He.
    In IEEE Transactions on Neural Networks and Learning Systems (IEEE TNNLS). Volume: 32, Issue: 4, April 2021.
  4. FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare. [PDF] [Link]
    Yiqiang Chen, Xin, Qin, Jindong Wang, Chaohui Yu, Wen Gao.
    In IEEE Intelligent Systems.
  5. Transfer Learning with Dynamic Distribution Adaptation. [PDF] [Link] [Code]
    Jindong Wang, Yiqiang Chen, Wenjie Feng, Han Yu, Meiyu Huang, Qiang Yang.
    In ACM Transactions on Intelligent Systems and Technology (ACM TIST). Volume 11, Issue 1, 2020. Pages 1-25.
  6. Cross-dataset Activity Recognition via Adaptive Spatial-temporal Transfer Learning. [PDF] [Link]
    Xin Qin, Yiqiang Chen, Jindong Wang, Chaohui Yu.
    In Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies (IMWUT). Volume 3, Issue 4, 2019. Pages 1-25. (Ubicomp-20 publications)
  7. Transfer Channel Prunning for Deep Unsupervised Domain Adaptation. [Link] [PDF] [Code]
    Chaohui Yu, Jindong Wang, Yiqiang Chen, Xin Qin.
    In International Journal of Machine Learning and Cybernetics (IJMLC). Volume 10, Issue 11, 2019. Pages 3129-3144.
  8. Multi-representation Adaptation Network for Cross-domain Image Classification. [Link] [PDF] [Code]
    Yongchun Zhu, Fuzhen Zhuang, Jindong Wang, Jingwu Chen, Zhiping Shi, Wenjuan Wu, Qing He.
    In Neural Networks (NEUNET). Volume 119, Nov. 2019. Pages 214-221.
  9. Cross-position Activity Recognition with Stratified Transfer Learning. [Link] [PDF]
    Yiqiang Chen, Jindong Wang, Meiyu Huang, Han Yu.
    In Pervasive and Mobile Computing (PMCJ). Volume 57, Jul. 2019. Pages 1-13
  10. Deep Learning for Sensor-based Activity Recognition: A Survey. [Link] [PDF]
    Jindong Wang, Yiqiang Chen, Shuji Hao, Xiaohui Peng, Lisha Hu.
    In Pattern Recognition Letters (PRL). Volume 119, Mar. 2019. Pages 3-11.
  11. OKRELM: Online Kernelized and Regularized Extreme Learning Machine for Wearable-based Activity Recognition. [Link] [PDF]
    Lisha Hu, Yiqiang Chen, Jindong Wang, Chunyu Hu, Xinlong Jiang.
    In International Journal of Machine Learning and Cybernetics (IJMLC). Volume 9, Issue 9, Sep. 2018. Pages 1577–1590.

Workshop papers

  1. FedHealth 2: Weighted Federated Transfer Learning via Batch Normalization for Personalized Healthcare. [ArXiv]
    Yiqiang Chen, Wang Lu, Jindong Wang, Xin Qin.
    In IJCAI-21 Workshop on Federated Machine Learning.
  2. FedHealth: A Federated Transfer Learning Framework for Wearable Healthcare. [PDF]
    Yiqiang Chen, Jindong Wang, Chaohui Yu, Wen Gao, Xin Qin.
    In IJCAI-19 Workshop on Federated Machine Learning. Macao, China. Aug. 10-16, 2019. Pages 1-8. (Best Application Paper)
  3. Transfer Channel Prunning for Deep Unsupervised Domain Adaptation. [Link] [PDF] [Code]
    Chaohui Yu, Jindong Wang, Yiqiang Chen, Xin Qin.
    In PAKDD-19 Workshop on Deep Learning for Knowledge Transfer. Macao, China. Apr. 2019.

Book chapters

  1. 深度学习500问. [京东] Invited for the transfer learning chapter. 2020
Talks
Projects
  1. Leading a pupular transfer learning resource projects on Github: Transfer Learning
  2. A unified Pytorch-based semi-supervised learning library: [TorchSSL]
  3. An easy-to-use speech recognition toolkit based on Espnet: EasyEspnet
  4. Leading the transfer learning tutorial (迁移学习简明手册) on Github: Tutorial
  5. I'm also leading other popular research projects: Machine Learning, Activity Recognition
  6. I started a software studio Pivot Studio with a group of talented people, and we made many applications. 2010-2014
Academic activities and awards
Academic service
Awards and Honors
Miscellaneous