FedTKD: a trustworthy heterogeneous federated learning based on adaptive knowledge distillation

• Main Authors: Chen, Leiming, Zhang, Weishan, Dong, Cihao, Zhao, Dehai, Zeng, Xingjie, Qiao, Sibo, Zhu, Yichang, Tan, Chee Wei
• Other Authors: School of Civil and Environmental Engineering
• Format: Article
• Language: English
• Published: 2024
• Subjects: Engineering; Malicious client identification; Knowledge distillation
• Online Access: https://hdl.handle.net/10356/174735
• Institution: Nanyang Technological University

Federated learning allows multiple parties to train models while jointly protecting user privacy. However, traditional federated learning requires each client to have the same model structure to fuse the global model. In real-world scenarios, each client may need to develop personalized models based...