Robust Aggregation for Federated Learning by Minimum <i>γ</i>-Divergence Estimation

Robust Aggregation for Federated Learning by Minimum <i>γ</i>-Divergence Estimation

Federated learning is a framework for multiple devices or institutions, called local clients, to collaboratively train a global model without sharing their data. For federated learning with a central server, an aggregation algorithm integrates model information sent from local clients to update the...

Full description

Bibliographic Details
Main Authors: Cen-Jhih Li, Pin-Han Huang, Yi-Ting Ma, Hung Hung, Su-Yun Huang
Format: Article
Language:English
Published: MDPI AG 2022-05-01
Series:Entropy
Subjects:
byzantine problem
density power divergence
federated learning
γ-divergence
influence function
robustness
Online Access:https://www.mdpi.com/1099-4300/24/5/686

Internet

https://www.mdpi.com/1099-4300/24/5/686

Similar Items