Hierarchical Federated Edge Learning With Adaptive Clustering in Internet of Things
- 12 August 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11 (21) , 34108-34122
Abstract
The expansion of the Internet of Things (IoT) has led to a significant surge in data flow over edge networks, posing substantial challenges to data mining and management. While federated edge learning (FEEL) effectively accomplishes global integration and local training based on the decentralized data sets, its deployment across expansive IoT networks introduces additional challenges. The primary issues stem from managing the interaction between the communication load and learning effectiveness. The communication loads driven by recurrent data exchanges between the user equipment (UE) and central servers exacerbate network congestion and latency issues. Moreover, the learning efficacy is undermined due to the typically nonindependent and identically distributed (non-IID) characteristics of real-world IoT data. In this article, a novel communication-efficient hierarchical FEEL framework is proposed to tackle these challenges. Specifically, UEs are adaptively clustered according to their link conditions, geographic locations, and data distributions. Small base stations (SBSs) collect local model updates from the UEs in their clusters and communicate with a macro base station (MBS) for the global model aggregation. To jointly maximize the communication gain (in terms of reducing latency) and the learning gain (in terms of improving accuracy), a clustering and resource allocation optimization problem is formulated, and a cross entropy-based method with low computational complexity is proposed. Numerical experiments validate that the proposed hierarchical FEEL system achieves fast convergence and significantly improves the system efficiency for various learning tasks and the system settings.Keywords
Funding Information
- National Natural Science Foundation of China (U20A20158, 62394292, U21B2029)
- Ministry of Industry and Information Technology (TC220H07E)
- Key Research and Development Program of Zhejiang Province (2023C01021)
- Fundamental Research Funds for the Central Universities (226-2024-00069)
- Zhejiang Provincial Natural Science Foundation of China (LR23F010006)
This publication has 30 references indexed in Scilit:
- Distance-Aware Hierarchical Federated Learning in Blockchain-Enabled Edge Computing NetworkIEEE Internet of Things Journal, 2023
- HED-FL: A hierarchical, energy efficient, and dynamic approach for edge Federated LearningPervasive and Mobile Computing, 2023
- Privacy-Preserving Asynchronous Federated Learning Framework in Distributed IoTIEEE Internet of Things Journal, 2023
- Semi-Federated Learning for Collaborative Intelligence in Massive IoT NetworksIEEE Internet of Things Journal, 2023
- Hierarchical Federated Learning with Adaptive Clustering on Non-IID Data2022
- JMSNAS: Joint Model Split and Neural Architecture Search for Learning over Mobile Edge Networks2022
- FedSA: A staleness-aware asynchronous Federated Learning algorithm with non-IID dataFuture Generation Computer Systems, 2021
- Model-Contrastive Federated Learning2021
- Privacy-preserving cloud computing on sensitive data: A survey of methods, products and challengesComputer Communications, 2019
- A Tutorial on the Cross-Entropy MethodAnnals of Operations Research, 2005