Can I read FedNorm: An Efficient Federated Learning Framework with Dual Heterogeneity Coexistence on Edge Intelligence Systems on EtoBox?

FedNorm: An Efficient Federated Learning Framework with Dual Heterogeneity Coexistence on Edge Intelligence Systems by Zirui Lian; Weihong Liu; Jing Cao; Zongwei Zhu; Xuehai Zhou is a scholarly article available to read on EtoBox.

What is FedNorm: An Efficient Federated Learning Framework with Dual Heterogeneity Coexistence on Edge Intelligence Systems about?

Federated learning (FL) is an emerging distributed learning paradigm, which aims to train machine learning models on geo-decentralized edge devices while keeping the training data stored locally. However, due to the scattered and diverse properties of edge devices, FL is often accompanied by typical heterogeneous features. One of the key challenges is statistical heterogeneity (aka non-independent identically distributed data, Non-IID), which leads to severe client-drift problem and unstable convergence. Moreover, the computational heterogeneity of devices can result in large computation time variation and thus exacerbate client-drift through inconsistent local training steps. The previous studies either ignore the client-drift problem or ignore the scatter in local gradient information, causing limited optimization effect. This paper proposes FedNorm framework to enable training Non-IID data on heterogeneous devices efficiently. First, a local model consistency update method is introduced to mitigate client-drift by allowing heterogeneous edge devices to implement different local training steps. Next, a federated gradient normalization method is introduced to reduce gradient scatt

Author

Zirui Lian; Weihong Liu; Jing Cao; Zongwei Zhu; Xuehai Zhou

Publisher

IEEE

Published

2022

Language

EN