mlsanityData to 7 Oct 2026

Encryption-Compatible Clustered Federated Learning via Distributed Expectation-Maximization over Metadata

arXiv 2607.28338 ↗First posted 30 Jul 2026cs.LG cs.CR cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Clustered Federated Learning (CFL) addresses data heterogeneity in federated settings by grouping clients with similar data distributions to enable effective training. Existing methods face a trade-off between privacy preservation, communication cost, and computational efficiency. We formalize this as the CFL trilemma, according to which improving two of these dimensions comes at the expense of the third. A prominent paradigm relies on metadata (i.e., low-dimensional representations of client datasets shared with the server) to enable communication- and computation-efficient clustering. However, such approaches are not compatible with standard FL privacy-preserving mechanisms. To address this limitation, we propose FLAMECHE, which reformulates metadata-based CFL as a distributed Expectation-Maximization (EM) procedure, restricting server updates to additive operations while preserving efficiency. This design enables compatibility with practical secure FL schemes. We conducted extensive experiments on multiple datasets under various heterogeneous scenarios. Results show that FLAMECHE improves the effectiveness of client models. It enables encryption-compatible metadata-based clustering, enhancing its positioning within the CFL trilemma.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 30 Jul 2026.

Builds on

22 of 38 references.

References · 22

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  3. 2019Advances and Open Problems in Federated Learningcited by 3,021
  4. 2016Deep Learning with Differential Privacycited by 2,682
  5. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
  6. 2020An Efficient Framework for Clustered Federated Learningcited by 505
  7. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 499
  8. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 222
  9. 2023Heterogeneous Federated Learning: State-of-the-art and Research Challengescited by 160
  10. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 112
  11. 2019Robust Federated Learning in a Heterogeneous Environmentcited by 88
  12. 2021Heterogeneity for the Win: One-Shot Federated Clusteringcited by 87
10 more
  1. 2021Federated Hyperparameter Tuning: Challenges, Baselines, and Connections to Weight-Sharingcited by 58
  2. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  3. 2015Deep Neural Networks with Random Gaussian Weights: A Universal Classification Strategy?cited by 40
  4. 2023Recent Advances on Federated Learning: A Systematic Surveycited by 40
  5. 2022Efficient Distribution Similarity Identification in Clustered Federated Learning via Principal Angles Between Client Data Subspacescited by 36
  6. 2023Contrastive encoder pre-training-based clustered federated learning for heterogeneous datacited by 5
  7. 2023StoCFL: A Stochastically Clustered Federated Learning Framework for Non-IID Data with Dynamic Client Participationcited by 4
  8. 2024Differentially Private Clustered Federated Learningcited by 4
  9. 2025FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shiftscited by 3
  10. 2025A survey on Clustered Federated Learning: Taxonomy, Analysis and Applicationscited by 2

Built on by

Not cited yet.