Genetic CFL: Optimization of Hyper-Parameters in Clustered Federated Learning
This addresses inefficiencies in clustered federated learning for edge computing applications, but it is incremental as it builds on existing methods with a novel hybrid approach.
The paper tackles the problem of degraded convergence and performance in federated learning due to non-IID data by proposing Genetic CFL, a hybrid algorithm that clusters edge devices and genetically optimizes hyper-parameters cluster-wise, resulting in significant improvements in individual cluster accuracy as benchmarked on MNIST and CIFAR-10 datasets.
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.