A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT
Saved in:
| Title: | A Novel Framework of Horizontal-Vertical Hybrid Federated Learning for EdgeIoT |
|---|---|
| Authors: | Li, K, Liang, Y, Yuan, X, Ni, W, Crowcroft, J, Yuen, C, Akan, OB |
| Contributors: | Apollo - University of Cambridge Repository |
| Source: | IEEE Networking Letters. 7:83-87 |
| Publication Status: | Preprint |
| Publisher Information: | Institute of Electrical and Electronics Engineers (IEEE), 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Signal Processing (eess.SP), FOS: Computer and information sciences, Distributed databases, horizontal and vertical, Computer Science - Machine Learning, Internet of Things, Data models, Federated learning, Servers, Computational modeling, Machine Learning (cs.LG), Fuzzy logic, non-IID data, Electronic mail, edge computing, Computer Science - Distributed, Parallel, and Cluster Computing, 4606 Distributed Computing and Systems Software, 46 Information and Computing Sciences, Radio frequency, FOS: Electrical engineering, electronic engineering, information engineering, Training, hybrid federated learning, Distributed, Parallel, and Cluster Computing (cs.DC), Electrical Engineering and Systems Science - Signal Processing |
| Description: | This letter puts forth a new hybrid horizontal-vertical federated learning (HoVeFL) for mobile edge computing-enabled Internet of Things (EdgeIoT). In this framework, certain EdgeIoT devices train local models using the same data samples but analyze disparate data features, while the others focus on the same features using non-independent and identically distributed (non-IID) data samples. Thus, even though the data features are consistent, the data samples vary across devices. The proposed HoVeFL formulates the training of local and global models to minimize the global loss function. Performance evaluations on CIFAR-10 and SVHN datasets reveal that the testing loss of HoVeFL with 12 horizontal FL devices and six vertical FL devices is 5.5% and 25.2% higher, respectively, compared to a setup with six horizontal FL devices and 12 vertical FL devices. |
| Document Type: | Article |
| File Description: | application/pdf |
| ISSN: | 2576-3156 |
| DOI: | 10.1109/lnet.2025.3540268 |
| DOI: | 10.17863/cam.118932 |
| DOI: | 10.48550/arxiv.2410.01644 |
| Access URL: | http://arxiv.org/abs/2410.01644 |
| Rights: | IEEE Copyright CC BY |
| Accession Number: | edsair.doi.dedup.....f9a8292ea5be0e98dd1863e9c4ef85d5 |
| Database: | OpenAIRE |
Full Text Finder 
Nájsť tento článok vo Web of Science | Abstract: | This letter puts forth a new hybrid horizontal-vertical federated learning (HoVeFL) for mobile edge computing-enabled Internet of Things (EdgeIoT). In this framework, certain EdgeIoT devices train local models using the same data samples but analyze disparate data features, while the others focus on the same features using non-independent and identically distributed (non-IID) data samples. Thus, even though the data features are consistent, the data samples vary across devices. The proposed HoVeFL formulates the training of local and global models to minimize the global loss function. Performance evaluations on CIFAR-10 and SVHN datasets reveal that the testing loss of HoVeFL with 12 horizontal FL devices and six vertical FL devices is 5.5% and 25.2% higher, respectively, compared to a setup with six horizontal FL devices and 12 vertical FL devices. |
|---|---|
| ISSN: | 25763156 |
| DOI: | 10.1109/lnet.2025.3540268 |