王琪玮 Qi-Wei Wang M.Sc. student, LAMDA Group School of Artificial Intelligence National Key Laboratory for Novel Software Technology Nanjing University, Nanjing 210023, China Email: wangqiwei@lamda.nju.edu.cn

Biography

Currently I am a first year graduate student of School of Artificial Intelligence in Nanjing University and a member of LAMDA Group, led by professor Zhi-Hua Zhou.

From July 2019 to August 2019,I was an intern at Center for Research on Intelligent Perception and Computing. I received my B.Sc. degree from College of Computer Science and Technology in Jilin University. In September 2021, I was admitted to study for a M.Sc. degree in Nanjing University without entrance examination,under the supervision of Assistant Researcher Han-Jia Ye and Professor De-Chuan Zhan.

Research Interests

My research interests include Machine Learning and Data Mining. Specifically, I focus on learning on extreme forms of data:

Class-Incremental Learning

• Class-Incremental Learning (i.e., CIL) aims to equip the model to incrementally adapt to new classes under a streaming data scenario. Notably, CIL also requires that the model remembers old knowledge without accessing much old data.

Learn Debiased Representation

• Learning Debiased Representation (i.e., Debiasing) aims to equip the model to learn unbiased knowledge from biased data or data with spurious correlations. Notably, Debiasing is essentially trying to improve the generalization of the model.

Preprints

• Da-Wei Zhou, Qi-Wei Wang, Zhi-Hong Qi, Han-Jia Ye, De-Chuan Zhan, Ziwei Liu. Deep Class-Incremental Learning: A Survey. arXiv:2302.03648, 2023. [arXiv][Code]

Publications

• Da-Wei Zhou, Qi-Wei Wang, Han-Jia Ye, De-Chuan Zhan. A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning. In: Eleventh International Conference on Learning Representations (ICLR'2023 Spotlight). [Paper][Code]

• Yi-Kai Zhang, Qi-Wei Wang, De-Chuan Zhan, Han-Jia Ye. Learning Debiased Representations via Conditional Attribute Interpolation. In: IEEE Conference on Computer Vision and Pattern Recognition (CVPR'2023). [Code]

Experience

2023.4 ~ Now, Tecent, WeChat. Research Intern

• I focus on the recommendation system in WeChat Channel (视频号).

Awards

• National Scholarship for Undergraduates,2018.11 and 2019.12

• 2023 Tencent Rhino-Bird Research Elite Program

Correspondence

Email: wangqiwei@lamda.nju.edu.cn
Address: National Key Laboratory for Novel Software Technology, Nanjing University, Xianlin Campus Mailbox 603, 163 Xianlin Avenue, Qixia District, Nanjing 210023, China