skip to main content
Language:
Search Limited to: Search Limited to: Resource type Show Results with: Show Results with: Search type Index

Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints

IEEE transaction on neural networks and learning systems, 2021-08, Vol.32 (8), p.3710-3722

ISSN: 2162-237X ;EISSN: 2162-2388 ;DOI: 10.1109/TNNLS.2020.3015958 ;PMID: 32833654 ;CODEN: ITNNAL

Digital Resources/Online E-Resources

Citations Cited by
  • Title:
    Clustered Federated Learning: Model-Agnostic Distributed Multitask Optimization Under Privacy Constraints
  • Author: Sattler, Felix ; Muller, Klaus-Robert ; Samek, Wojciech
  • Subjects: Clustering ; Data models ; distributed learning ; federated learning ; multi-task learning ; Optimization ; Privacy ; Servers ; Sociology ; Statistics ; Training
  • Is Part Of: IEEE transaction on neural networks and learning systems, 2021-08, Vol.32 (8), p.3710-3722
  • Description: Federated learning (FL) is currently the most widely adopted framework for collaborative training of (deep) machine learning models under privacy constraints. Albeit its popularity, it has been observed that FL yields suboptimal results if the local clients' data distributions diverge. To address this issue, we present clustered FL (CFL), a novel federated multitask learning (FMTL) framework, which exploits geometric properties of the FL loss surface to group the client population into clusters with jointly trainable data distributions. In contrast to existing FMTL approaches, CFL does not require any modifications to the FL communication protocol to be made, is applicable to general nonconvex objectives (in particular, deep neural networks), does not require the number of clusters to be known a priori , and comes with strong mathematical guarantees on the clustering quality. CFL is flexible enough to handle client populations that vary over time and can be implemented in a privacy-preserving way. As clustering is only performed after FL has converged to a stationary point, CFL can be viewed as a postprocessing method that will always achieve greater or equal performance than conventional FL by allowing clients to arrive at more specialized models. We verify our theoretical analysis in experiments with deep convolutional and recurrent neural networks on commonly used FL data sets.
  • Publisher: IEEE
  • Language: English
  • Identifier: ISSN: 2162-237X
    EISSN: 2162-2388
    DOI: 10.1109/TNNLS.2020.3015958
    PMID: 32833654
    CODEN: ITNNAL
  • Source: IEEE Open Access Journals
Back to results list
INSPIRE LIBRARY - TON DUC THANG UNIVERSITY (84-028) 37 755 057 Feedback
19 Nguyen Huu Tho St. Dist.7, HCM thuvien@tdtu.edu.vn

Copyright © 2017 INSPIRE LIBRARY - TON DUC THANG UNIVERSITY

Searching Remote Databases, Please Wait