Back to Search
Start Over
Genetic CFL: Optimization of Hyper-Parameters in Clustered Federated Learning
- Source :
- Computational Intelligence and Neuroscience, vol. 2021, Article ID 7156420, 10 pages, 2021
- Publication Year :
- 2021
-
Abstract
- Federated learning (FL) is a distributed model for deep learning that integrates client-server architecture, edge computing, and real-time intelligence. FL has the capability of revolutionizing machine learning (ML) but lacks in the practicality of implementation due to technological limitations, communication overhead, non-IID (independent and identically distributed) data, and privacy concerns. Training a ML model over heterogeneous non-IID data highly degrades the convergence rate and performance. The existing traditional and clustered FL algorithms exhibit two main limitations, including inefficient client training and static hyper-parameter utilization. To overcome these limitations, we propose a novel hybrid algorithm, namely genetic clustered FL (Genetic CFL), that clusters edge devices based on the training hyper-parameters and genetically modifies the parameters cluster-wise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyper-parameter optimization. The results are bench-marked using MNIST handwritten digit dataset and the CIFAR-10 dataset. The proposed genetic CFL shows significant improvements and works well with realistic cases of non-IID and ambiguous data.<br />Comment: 7 pages, 4 figures, 4 tables
- Subjects :
- Computer Science - Artificial Intelligence
Subjects
Details
- Database :
- arXiv
- Journal :
- Computational Intelligence and Neuroscience, vol. 2021, Article ID 7156420, 10 pages, 2021
- Publication Type :
- Report
- Accession number :
- edsarx.2107.07233
- Document Type :
- Working Paper
- Full Text :
- https://doi.org/10.1155/2021/7156420