2025
Rising from Ashes: Generalized Federated Learning via Dynamic Parameter Reset
A novel FL framework is presented, FedPhoenix, that stochastically re-sets partial parameters in each round to destroy some features of the global model, guiding FL training to learn multiple generalized features for inference rather than specific overfitting features.
Jia-Hao Wu, Ming Hu, Yanxin Yang et al.
· Neural Information Processin... · 1 citation