Federated learning (FL)
2 articles · search the full text for this term
-
An Adaptive and Privacy-Aware Federated Learning Framework for Efficient and Secure Model Training Across Heterogeneous Datasets
Abstract: The problem of efficiency and privacy regarding heterogeneous data in modern distributed machine learning systems is a vital point that should be taken into account. The absence of IID data distribution, client heterogeneity, and privacy invasion during the aggregation model are the bane of conventional federated learning (FL) approaches to learning like FedAvg and FedProx. The paper proposes that the adaptive and privacy-aware FL framework (AFL-P) can be used to …
Published in Journal of Mobile Computing, Communications & Mobile Networks · Vol. 13, Issue 1, 2026 · pp. 16–25 Read article
-
Federated Learning: A Comprehensive Review of Models, Algorithms, and Business Applications
Abstract: In an age where data privacy is a significant concern, federated learning (FL) has become a game-changing method in machine learning. This decentralized model enables various parties to work together on training models without exchanging their raw data, effectively tackling the issues posed by data silos and privacy regulations. This article explores the current state of FL, including its underlying models and algorithms, practical applications, benefits, challenges, and future directions. …
Published in Current Trends in Information Technology · Vol. 14, Issue 3, 2024 · pp. 1–9 Read article