News


23 Sep 2024
One paper is accepted by ACM TORS on recommendation unlearning.

17 May 2024
One paper is accepted by KDD 2024 on multi-task learning for recommendation.

20 Oct 2023
One paper is accepted by WSDM 2024 about label learning for short video recommendation.

5 Aug 2023
One paper is accepted by CIKM 2023 about label debiasing for short video recommendation.

Yimeng Bai 

Email: baiyimeng77@gmail.com
• GitHub • Google Scholar
• DBLP • ORCID

I am currently in the first year of my PhD program at Lab for Data Science, USTC, with a research focus on recommender systems, particularly generative recommendation.

Education

University of Science and Technology of China (USTC)
PhD student in Cyber Science and Technology     Sep. 2022 - Now, Hefei, China
Advisor: Prof. Fuli Feng    Mentor: Dr. Yang Zhang
Beijing Jiaotong University (BJTU)
Bachelor in Science     Sep. 2018 - Jun. 2022, Beijing, China

Experiences

Research Intern, Kuaishou, Dec. 2022 - Aug. 2024
Mentor: Dr. Jing Lu  
Research Intern, ByteDance (TikTok), Sep. 2024 - Now
Mentor: Shaohui Ruan  

Publications


In the Year of 2024:


pdf		 Recommendation Unlearning via Influence Function
Yang Zhang, Zhiyu Hu, Yimeng Bai, Jiancan Wu, Qifan Wang, Fuli Feng
ACM TORS (Original Research).    Codes  

pdf		 GradCraft: Elevating Multi-task Recommendations through Holistic Gradient Crafting
Yimeng Bai, Yang Zhang, Fuli Feng, Jing Lu, Xiaoxue Zang, Chenyi Lei, Yang Song
KDD 2024 (Applied Data Science, Acceptance Rate: 20%)    Codes

pdf		 LabelCraft: Empowering Short Video Recommendations with Automated Label Crafting
Yimeng Bai, Yang Zhang, Jing Lu, Jianxin Chang, Xiaoxue Zang, Yanan Niu, Yang Song, Fuli Feng
WSDM 2024 (Poster, Acceptance Rate: 18%).    Codes
In the Year of 2023:


pdf		 Leveraging Watch-time Feedback for Short-Video Recommendations: A Causal Labeling Framework
Yang Zhang, Yimeng Bai, Jianxin Chang, Xiaoxue Zang, Song Lu, Jing Lu, Fuli Feng, Yanan Niu, Yang Song
CIKM 2023 (Applied Research Paper, Acceptance Rate: 32%).   

Last update: Oct. 2024. Webpage template borrows from Prof. Xiangnan He.