Ximei Wang

Ximei Wang

I am currently a senior researcher in Tencent, focusing on dataset shift in machine learning, especially transfer learning, domain adaptation, cross-domain recommendation, multi-domain learning and multi-task learning. Prior to that, I received my Ph.D. degree from School of Software, Tsinghua University, advised by Prof. Jianmin Wang and Prof. Mingsheng Long. During my Ph.D. study, I was a research intern in Tencent for a year, mentored by Junwei Pan. I received my B.S. degree from Department of Automation, Tsinghua University.

messixmwang [AT] tencent.com, wxm17 [AT] tsinghua.org.cn
[Google Scholar] [Semantic Scholar] [ResearchGate]
Binhai Building, Tencent, Shenzhen, China

Recent News

Education

Preprint

(* Equal Contribution, # Corresponding Author)

  1. On the Embedding Collapse when Scaling up Recommendation Models
    Xingzhuo Guo, Junwei Pan, Ximei Wang, Baixu Chen, Jie Jiang, Mingsheng Long [arXiv]

  2. Decoupled Training: Return of Frustratingly Easy Multi-Domain Learning
    Ximei Wang, Junwei Pan, Xingzhuo Guo, Dapeng Liu, Jie Jiang [arXiv]

  3. STEM: Unleashing the Power of Embeddings for Multi-task Recommendation
    Liangcai Su, Junwei Pan, Ximei Wang, Xi Xiao, Shijie Quan, Xihua Chen, Jie Jiang [arXiv]

Publications

(* Equal Contribution, # Corresponding Author)

  1. ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning
    Junguang Jiang, Baixu Chen, Junwei Pan, Ximei Wang, Liu Dapeng, Jie Jiang, Mingsheng Long
    Neural Information Processing Systems (NeurIPS), 2023 [arXiv]

  2. Bi-Tuning: Efficient Transfer from Pre-Trained Models
    Jincheng Zhong, Haoyu Ma, Ximei Wang, Zhi Kou, Mingsheng Long
    European Conference on Machine Learning (ECML), 2023 [PDF] [arXiv] [Code]

  3. CLIPood: Generalizing CLIP to Out-of-Distributions
    Yang Shu, Xingzhuo Guo, Jialong Wu, Ximei Wang, Jianmin Wang, Mingsheng Long
    International Conference on Machine Learning (ICML), 2023 [PDF] [arXiv] [Code]

  4. AdaTask: A Task-aware Adaptive Learning Rate Approach to Multi-task Learning
    Enneng Yang, Junwei Pan, Ximei Wang, Haibin Yu, Li Shen, Xihua Chen, Lei Xiao, Jie Jiang, Guibing Guo
    AAAI Conference on Artificial Intelligence (AAAI), 2023 [pdf] (Oral)

  5. Debiased Self-Training for Semi-Supervised Learning
    Baixu Chen, Junguang Jiang, Ximei Wang, Pengfei Wan, Jianmin Wang, Mingsheng Long
    Neural Information Processing Systems (NeurIPS), 2022 [PDF] [arXiv] [PDF] [Code] (Oral)

  6. X-model: Improving Data Efficiency in Deep Learning with A Minimax Model
    Ximei Wang, Xinyang Chen, Jianmin Wang, Mingsheng Long
    International Conference on Learning Representations (ICLR), 2022 [OpenReview]

  7. Self-Tuning for Data-Efficient Deep Learning
    Ximei Wang*, Jinghan Gao*, Jianmin Wang, Mingsheng Long#
    International Conference on Machine Learning (ICML), 2021 [PDF] [Code] [Slide] [Video] [Poster] [Blog] [Zhihu] [SlidesLive]

  8. Transferable Calibration with Lower Bias and Variance in Domain Adaptation
    Ximei Wang, Mingsheng Long#, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NeurIPS), 2020 [PDF] [Appendix] [Code] [Poster] [Slide] [Video]

  9. Transferable Normalization: Towards Improving Transferability of Deep Neural Networks
    Ximei Wang, Ying Jin, Mingsheng Long#, Jianmin Wang, Michael I. Jordan
    Neural Information Processing Systems (NeurIPS), 2019 [PDF] [Code] [Poster] [Slide]

  10. Transferable Attention for Domain Adaptation
    Ximei Wang, Liang Li, Weirui Ye, Mingsheng Long#, Jianmin Wang
    AAAI Conference on Artificial Intelligence (AAAI), 2019 [PDF] (Oral)

  11. Regressive Domain Adaptation for Unsupervised Keypoint Detection
    Junguang Jiang, Yifei Ji, Ximei Wang, Yufeng Liu, Jianmin Wang, Mingsheng Long
    IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2021 [PDF] [Code]

  12. Resource Efficient Domain Adaptation
    Junguang Jiang, Ximei Wang, Mingsheng Long#, Jianmin Wang
    ACM International Conference on Multimedia (ACMMM), 2020 [PDF] [Code]

  13. Minimum Class Confusion for Versatile Domain Adaptation
    Ying Jin, Ximei Wang, Mingsheng Long#, Jianmin Wang
    European Conference on Computer Vision (ECCV), 2020 [PDF] [Code]

  14. Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
    Kaichao You, Ximei Wang, Mingsheng Long#, Michael I. Jordan
    International Conference on Machine Learning (ICML), 2019 [PDF] [Code]

Teaching Assistant (TA)

Professional Services

Program Committee Member

Peer Reviewer

Awards