Zhu, R. (author), Yang, M. (author), Yang, J. (author), Wang, Q. (author) Federated Learning (FL) is an important privacy-preserving learning paradigm that is expected to play an essential role in the future Intelligent Internet of Things (IoT). However, model training in FL is vulnerable to noise and the statistical heterogeneity of local data across IoT clients. In this paper, we propose FedNaWi, a “Go Narrow, Then...
conference paper 2023