Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning

Shaashwat Agrawal, Sagnik Sarkar, Mamoun Alazab, Praveen Kumar Reddy Maddikunta, Thippa Reddy Gadekallu, Quoc Viet Pham

    Research output: Contribution to journalArticlepeer-review

    16 Downloads (Pure)


    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 hyperparameter 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 hyperparameters and genetically modifies the parameters clusterwise. Then, we introduce an algorithm that drastically increases the individual cluster accuracy by integrating the density-based clustering and genetic hyperparameter 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. An accuracy of 99.79% is observed in the MNIST dataset and 76.88% in CIFAR-10 dataset with only 10 training rounds.

    Original languageEnglish
    Article number7156420
    Pages (from-to)1-10
    Number of pages10
    JournalComputational Intelligence and Neuroscience
    Publication statusPublished - 2021


    Dive into the research topics of 'Genetic CFL: Hyperparameter Optimization in Clustered Federated Learning'. Together they form a unique fingerprint.

    Cite this