MATHEMATICAL MODELING AND COMPUTATIONAL ANALYSIS OF  FEDERATED LEARNING CONVERGENCE IN HETEROGENEOUS  EDGE INTELLIGENCE SYSTEMS

Kumbala Pradeep Reddy,S Jagadeesh,  B. Narendra Kumar

MATHEMATICAL MODELING AND COMPUTATIONAL ANALYSIS OF FEDERATED LEARNING CONVERGENCE IN HETEROGENEOUS EDGE INTELLIGENCE SYSTEMS

Authors

Kumbala Pradeep Reddy,S Jagadeesh, B. Narendra Kumar

Keywords:

Federated Learning, Edge Intelligence, Convergence Analysis, Mathematical Modeling, Distributed Machine Learning, Heterogeneous Networks, Computational Optimization.

Abstract

Federated Learning (FL) has emerged as a promising distributed machine learning paradigm that enablescollaborative model training across multiple edge devices without requiring the exchange of raw data. This capability addresses growing concerns related to data privacy, communication overhead, and regulatory compliancein modern edge intelligence systems

References

H. B. McMahan et al., “Communication-Efficient Learning of Deep Networks from Decentralized Data,” AISTATS, 2017.

J. Konečný et al., “Federated Learning: Strategies for Improving Communication Efficiency,” NIPS Workshop, 2016

Downloads

Published

2023-09-20

How to Cite

Kumbala Pradeep Reddy,S Jagadeesh, B. Narendra Kumar. (2023). MATHEMATICAL MODELING AND COMPUTATIONAL ANALYSIS OF FEDERATED LEARNING CONVERGENCE IN HETEROGENEOUS EDGE INTELLIGENCE SYSTEMS. Journal of Computational Analysis and Applications (JoCAAA), 31(4), 2999–3007. Retrieved from https://eudoxuspress.com/index.php/pub/article/view/5550