I’m Sanshi Lei Yu, or 余磊 (legal name), a postgraduate student in USTC and BDAA Lab. My advisor is Qi Liu.

I received my Bachelor of Engineering degree from USTC in 2021.


My research focuses on recommendation system.


  • Sanshi Lei Yu, Qi Liu, Fei Wang, Yang Yu and Enhong Chen. Federated News Recommendation with Fine-grained Interpolation and Dynamic Clustering. The 32nd ACM International Conference on Information and Knowledge Management (CIKM 2023). [Paper] [Code] [Slide].
  • Sanshi Lei Yu*, Zhuoxuan Jiang*, Dong-Dong Chen, Shanshan Feng, Dongsheng Li, Qi Liu, Jinfeng Yi. Leveraging Tripartite Interaction Information from Live Stream E-Commerce for Improving Product Recommendation. The 27th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2021). [Paper] [Code] [Slide] [Talk].
  • Yang Yu, Qi Liu, Likang Wu, Runlong Yu, Sanshi Lei Yu, Zaixi Zhang. Untargeted Attack against Federated Recommendation Systems via Poisonous Item Embeddings and the Defense. The 37th AAAI Conference on Artificial Intelligence (AAAI 2023). [Paper] [Code].

      * for equal contributions.


  • news-recommendation: Implementations of some methods in news recommendation.
  • emgithub: Embed a file from GitHub repository just like GitHub Gist.
  • RecHub: A library for GNN-based recommendation system featuring heterogeneous GNN training.