Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency
Federated Learning (FL) is a distributed machine-learning paradigm that enables models to be trained across multiple decentralized devices or servers holding local data without transferring the raw data to a central location. However, applying FL to heterogeneous IoT scenarios comes with several cha...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/17/1/18 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832588406923722752 |
|---|---|
| author | Chen Qiu Ziang Wu Haoda Wang Qinglin Yang Yu Wang Chunhua Su |
| author_facet | Chen Qiu Ziang Wu Haoda Wang Qinglin Yang Yu Wang Chunhua Su |
| author_sort | Chen Qiu |
| collection | DOAJ |
| description | Federated Learning (FL) is a distributed machine-learning paradigm that enables models to be trained across multiple decentralized devices or servers holding local data without transferring the raw data to a central location. However, applying FL to heterogeneous IoT scenarios comes with several challenges due to the diverse nature of these devices in terms of hardware capabilities, communications, and data heterogeneity. Furthermore, the conventional parameter server-based FL paradigm aggregates the trained parameters of devices directly, which incurs high communication overhead. To this end, this paper designs a hierarchical federated-learning framework for heterogeneous IoT systems, focusing on enhancing communication efficiency and ensuring data security through lightweight encryption. By leveraging hierarchical aggregation, lightweight stream encryption, and adaptive device participation, the proposed framework provides an efficient and robust solution for federated learning in dynamic and resource-constrained IoT environments. The extensive experimental results show that the proposed FL paradigm significantly reduces round time by 20%. |
| format | Article |
| id | doaj-art-41309863599641a286187ab45740ba79 |
| institution | Kabale University |
| issn | 1999-5903 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj-art-41309863599641a286187ab45740ba792025-01-24T13:33:34ZengMDPI AGFuture Internet1999-59032025-01-011711810.3390/fi17010018Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication EfficiencyChen Qiu0Ziang Wu1Haoda Wang2Qinglin Yang3Yu Wang4Chunhua Su5Graduate School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu 965-8580, Fukushima Prefecture, JapanGraduate School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu 965-8580, Fukushima Prefecture, JapanGraduate School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu 965-8580, Fukushima Prefecture, JapanCyberspace Institute of Advanced Technology/Huangpu Research School of Guangzhou University, Guangzhou University (Huangpu), Guangzhou 510006, ChinaInstitute of Artificial Intelligence and Blockchain, Guangzhou University, Guangzhou 510006, ChinaGraduate School of Computer Science and Engineering, University of Aizu, Aizuwakamatsu 965-8580, Fukushima Prefecture, JapanFederated Learning (FL) is a distributed machine-learning paradigm that enables models to be trained across multiple decentralized devices or servers holding local data without transferring the raw data to a central location. However, applying FL to heterogeneous IoT scenarios comes with several challenges due to the diverse nature of these devices in terms of hardware capabilities, communications, and data heterogeneity. Furthermore, the conventional parameter server-based FL paradigm aggregates the trained parameters of devices directly, which incurs high communication overhead. To this end, this paper designs a hierarchical federated-learning framework for heterogeneous IoT systems, focusing on enhancing communication efficiency and ensuring data security through lightweight encryption. By leveraging hierarchical aggregation, lightweight stream encryption, and adaptive device participation, the proposed framework provides an efficient and robust solution for federated learning in dynamic and resource-constrained IoT environments. The extensive experimental results show that the proposed FL paradigm significantly reduces round time by 20%.https://www.mdpi.com/1999-5903/17/1/18hierarchical federated learninglightweightheterogeneous device |
| spellingShingle | Chen Qiu Ziang Wu Haoda Wang Qinglin Yang Yu Wang Chunhua Su Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency Future Internet hierarchical federated learning lightweight heterogeneous device |
| title | Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency |
| title_full | Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency |
| title_fullStr | Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency |
| title_full_unstemmed | Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency |
| title_short | Hierarchical Aggregation for Federated Learning in Heterogeneous IoT Scenarios: Enhancing Privacy and Communication Efficiency |
| title_sort | hierarchical aggregation for federated learning in heterogeneous iot scenarios enhancing privacy and communication efficiency |
| topic | hierarchical federated learning lightweight heterogeneous device |
| url | https://www.mdpi.com/1999-5903/17/1/18 |
| work_keys_str_mv | AT chenqiu hierarchicalaggregationforfederatedlearninginheterogeneousiotscenariosenhancingprivacyandcommunicationefficiency AT ziangwu hierarchicalaggregationforfederatedlearninginheterogeneousiotscenariosenhancingprivacyandcommunicationefficiency AT haodawang hierarchicalaggregationforfederatedlearninginheterogeneousiotscenariosenhancingprivacyandcommunicationefficiency AT qinglinyang hierarchicalaggregationforfederatedlearninginheterogeneousiotscenariosenhancingprivacyandcommunicationefficiency AT yuwang hierarchicalaggregationforfederatedlearninginheterogeneousiotscenariosenhancingprivacyandcommunicationefficiency AT chunhuasu hierarchicalaggregationforfederatedlearninginheterogeneousiotscenariosenhancingprivacyandcommunicationefficiency |