mlsanityData to 7 Oct 2026

Genetic CFL: Optimization of Hyper-Parameters in Clustered Federated Learning

arXiv 2107.07233 ↗First posted 15 Jul 2021cs.AIcited by 6

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 13 of its 31 references that are in the map. First posted on arXiv 15 Jul 2021.

Builds on

13 of 31 references.

References · 13

  1. 2018Federated Learning with Non-IID Datacited by 1,099
  2. 2019Towards Federated Learning at Scale: System Designcited by 826
  3. 2020Federated Learning with Matched Averagingcited by 564
  4. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  5. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
  6. 2018Applied Federated Learning: Improving Google Keyboard Query Suggestionscited by 202
  7. 2020TiFL: A Tier-based Federated Learning Systemcited by 95
  8. 2021Fusion of Federated Learning and Industrial Internet of Things: A Surveycited by 28
  9. 2021FEDZIP: A Compression Framework for Communication-Efficient Federated Learningcited by 27
  10. 2021Time-Correlated Sparsification for Communication-Efficient Federated Learningcited by 25
  11. 2021UAV Communications for Sustainable Federated Learningcited by 15
  12. 2020FedCD: Improving Performance in non-IID Federated Learningcited by 13
1 more
  1. 2020Efficient Hyperparameter Optimization in Deep Learning Using a Variable Length Genetic Algorithmcited by 13

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 2; 2024: 1; 2025: 2.

6 papers.

  1. 2023FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descentcited by 8
  2. 2022FEATHERS: Federated Architecture and Hyperparameter Searchcited by 3
  3. 2023Adaptive Federated Learning via New Entropy Approachcited by 3
  4. 2025A survey on Clustered Federated Learning: Taxonomy, Analysis and Applicationscited by 2
  5. 2024DistDD: Distributed Data Distillation Aggregation through Gradient Matchingcited by 0
  6. 2025FedBWO: Enhancing Communication Efficiency in Federated Learningcited by 0