FedHD: communication-efficient federated learning from hybrid data

DOI10.1016/J.JFRANKLIN.2023.06.039MaRDI QIDQ6177550zbMATH OpenFDO

Authors Haiqing Gao, Songyang Ge, Tsung-Hui Chang

Publication date 31 August 2023

Published in Journal of the Franklin Institute (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/J.JFRANKLIN.2023.06.039

Mathematics Subject Classification ID

Computer science (68-XX)

Recommendations

• Towards efficient communications in federated learning: a contemporary survey
• A Novel Framework for the Analysis and Design of Heterogeneous Federated Learning
• Advances and Open Problems in Federated Learning
• Over-the-Air Federated Learning From Heterogeneous Data

Cites work

• Advances and Open Problems in Federated Learning
• Deep learning
• Distributed optimization and statistical learning via the alternating direction method of multipliers
• Gradient descent optimizes over-parameterized deep ReLU networks
• Optimization methods for large-scale machine learning
• Supervised Learning Under Distributed Features

Cited in

(1)

• A digital over-the-air computation system based on maximum posterior probability demodulation

This page was built for publication: FedHD: communication-efficient federated learning from hybrid data

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6177550)