Zhe Li

Conference Papers

• Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization.
  Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, and Haibo Yang.
  ICLR 2025. (acceptance rate: 32.08%)
  [Code] [FL@FM-NeurIPS'24 Workshop Version]

• FAST: A Lightweight Mechanism Unleashing Arbitrary Client Participation in Federated Learning.
  Zhe Li, Seyedsina Nabavirazavi, Bicheng Ying, Sitharama Iyengar, and Haibo Yang.
  IJCAI 2025. (acceptance rate: 19.3%)
  [Code]

Preprints and Submitted Papers

• Reconciling Hessian-Informed Acceleration and Scalar-Only Communication for Efficient Federated Zeroth-Order Fine-Tuning.
  Zhe Li, Bicheng Ying, Zidong Liu, Chaosheng Dong, and Haibo Yang.
  Under review.
  

• Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable.
  Bicheng Ying, Zhe Li, and Haibo Yang.
  Under review.
  

• Exploring LLMs' Potential for Privacy Leakage Detection in Android App Logs: An Empirical Study.
  Zhiyuan Chen, Vanessa Nava-Camal, Tiash Roy, Zhe Li, Yiming Tang, Xueling Zhang, and Haibo Yang.
  IEEE Software, submitted.