Biography

I am currently an assistant professor at the School of Computing and Artificial Intelligence, Shanghai University of Finance and Economics. Before that, I obtained my Ph.D. at the Hong Kong University of Science and Technology under the supervision of Prof. Kai Chen and Prof. Qiang Yang. I have also collaborated closely with Prof. Leye Wang and Prof. Junxue Zhang. My research interests focus on developing secure, accurate, and high-performance machine learning systems.

Email: chaidi[at]mail[dot]sufe[dot]edu[dot]cn

团队长期招募机器学习系统、人工智能安全方向的硕士与博士同学，如果你对构建数据-算法协同驱动的机器学习系统有着浓厚兴趣或独特看法，欢迎联系我，让我们一起做出世界一流的研究成果！

Publications

• Unlocking Full Efficiency of Token Filtering in Large Language Model Training. [Paper]
  Di Chai, Pengbo Li, Feiyuan Zhang, Yilun Jin, Han Tian, Kaiqiang Xu, Binhang Yuan, Dian Shen, Junxue Zhang, Kai Chen.
  ICLR’26 [CCF-A]

• Efficient Decentralized Federated Singular Vector Decomposition. [Paper] [Code]
  Di Chai, Junxue Zhang, Liu Yang, Yilun Jin, Leye Wang, Kai Chen, Qiang Yang.
  USENIX ATC’24 [CCF-A]

• A Survey for Federated Learning Evaluations: Goals and Measures. [Paper] [Code]
  Di Chai, Leye Wang, Liu Yang, Junxue Zhang, Kai Chen, Qiang Yang.
  IEEE TKDE’24 [CCF-A]

• Practical Lossless Federated Singular Vector Decomposition Over Billion-Scale Data. [Paper] [Code]
  Di Chai, Leye Wang, Junxue Zhang, Liu Yang, Shuowei Cai, Kai Chen, Qiang Yang.
  ACM SIGKDD’22 [CCF-A]

• Secure Federated Matrix Factorization. [Paper] [Code]
  Di Chai, Leye Wang, Kai Chen, Qiang Yang.
  IEEE Intelligent Systems’21 [400+ Citations]

• Efficient Federated Matrix Factorization against Inference Attacks. [Paper]
  Di Chai, Leye Wang, Kai Chen, Qiang Yang.
  ACM TIST’21

• Bike Flow Prediction with Multi-Graph Convolutional Networks. [Paper] [Code]
  Di Chai, Leye Wang, Qiang Yang.
  ACM SIGSPATIAL’18 [350+ Citations]

• Sequoia: An Accessible and Extensible Framework for Privacy-Preserving Machine Learning over Dis- tributed Data. [Paper]
  Kaiqiang Xu, Di Chai, Junxue Zhang, Fan Lai, Kai Chen.
  ACM SIGMOD’25 [CCF-A]

• Exploring the Generalizability of Spatio-Temporal Traffic Prediction: Meta-Modeling and an Analytic Framework. [Paper] [Code]
  Leye Wang, Di Chai, Xuanzhe Liu, Liyue Chen, Kai Chen.
  IEEE TKDE’23 [CCF-A]

• Sphinx: Enabling privacy-preserving online learning over the cloud. [Paper]
  Han Tian, Chaoliang Zeng, Zhenghang Ren, Di Chai, Junxue Zhang, Kai Chen, Qiang Yang.
  IEEE S&P’22 [CCF-A]

• Practical and secure federated recommendation with personalized mask. [Paper]
  Liu Yang, Junxue Zhang, Di Chai, Leye Wang, Kun Guo, Kai Chen, Qiang Yang.
  FL-IJCAI’22

• Secure forward aggregation for vertical federated neural networks. [Paper]
  Shuowei Cai, Di Chai, Liu Yang, Junxue Zhang, Yilun Jin, Leye Wang, Kun Guo, Kai Chen.
  FL-IJCAI’22

• Aegis: A Trusted, Automatic and Accurate Verification Framework for Vertical Federated Learning. [Paper]
  Cengguang Zhang, Junxue Zhang, Di Chai, Kai Chen.
  FL-IJCAI’21 [Best Application Award].