mlsanityData to 14 Oct 2026

Towards Client Driven Federated Learning

arXiv 2405.15407 ↗First posted 24 May 2024cs.LG cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Conventional federated learning (FL) frameworks follow a server-driven model where the server determines session initiation and client participation, which faces challenges in accommodating clients' asynchronous needs for model updates. We introduce Client-Driven Federated Learning (CDFL), a novel FL framework that puts clients at the driving role. In CDFL, each client independently and asynchronously updates its model by uploading the locally trained model to the server and receiving a customized model tailored to its local task. The server maintains a repository of cluster models, iteratively refining them using received client models. Our framework accommodates complex dynamics in clients' data distributions, characterized by time-varying mixtures of cluster distributions, enabling rapid adaptation to new tasks with superior performance. In contrast to traditional clustered FL protocols that send multiple cluster models to a client to perform distribution estimation, we propose a paradigm that offloads the estimation task to the server and only sends a single model to a client, and novel strategies to improve estimation accuracy. We provide a theoretical analysis of CDFL's convergence. Extensive experiments across various datasets and system settings highlight CDFL's substantial advantages in model performance and computation efficiency over baselines.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 29 of its 45 references that are in the map. First posted on arXiv 24 May 2024.

Builds on

29 of 45 references.

References · 29

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2016Matching Networks for One Shot Learningcited by 2,255
  4. 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
  5. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  6. 2019Clustered Federated Learning: Model-Agnostic Distributed Multi-Task Optimization under Privacy Constraintscited by 503
  7. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 459
  8. 2020Adaptive Personalized Federated Learningcited by 358
  9. 2020Three Approaches for Personalization with Applications to Federated Learningcited by 325
  10. 2019Asynchronous Federated Optimizationcited by 267
  11. 2020Federated learning with hierarchical clustering of local updates to improve training on non-IID datacited by 223
  12. 2021Federated Learning with Buffered Asynchronous Aggregationcited by 190
17 more
  1. 2020Federated Continual Learning with Weighted Inter-client Transfercited by 161
  2. 2021Multi-Center Federated Learning: Clients Clustering for Better Personalizationcited by 113
  3. 2021Asynchronous Federated Learning on Heterogeneous Devices: A Surveycited by 93
  4. 2019SAFA: a Semi-Asynchronous Protocol for Fast Federated Learning with Low Overheadcited by 82
  5. 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
  6. 2020FedGroup: Efficient Clustered Federated Learning via Decomposed Data-Driven Measurecited by 46
  7. 2021FedSoft: Soft Clustered Federated Learning with Proximal Local Updatingcited by 46
  8. 2022On the Convergence of Clustered Federated Learningcited by 31
  9. 2023Personalized Online Federated Learning with Multiple Kernelscited by 11
  10. 2021CSAFL: A Clustered Semi-Asynchronous Federated Learning Frameworkcited by 10
  11. 2022Multi-Edge Server-Assisted Dynamic Federated Learning with an Optimized Floating Aggregation Pointcited by 10
  12. 2024Model Supply Chain Poisoning: Backdooring Pre-trained Models via Embedding Indistinguishabilitycited by 6
  13. 2022Asynchronous Hierarchical Federated Learningcited by 4
  14. 2021User-Centric Federated Learningcited by 3
  15. 2023User-Centric Federated Learning: Trading off Wireless Resources for Personalizationcited by 3
  16. 2022An Improved Algorithm for Clustered Federated Learningcited by 2
  17. 2023Asynchronous Online Federated Learning with Reduced Communication Requirementscited by 2

Built on by

Not cited yet.