FedCliP: Federated Learning with Client Pruning
Not on the map. Why?
Abstract (arXiv)
The prevalent communication efficient federated learning (FL) frameworks usually take advantages of model gradient compression or model distillation. However, the unbalanced local data distributions (either in quantity or quality) of participating clients, contributing non-equivalently to the global model training, still pose a big challenge to these works. In this paper, we propose FedCliP, a novel communication efficient FL framework that allows faster model training, by adaptively learning which clients should remain active for further model training and pruning those who should be inactive with less potential contributions. We also introduce an alternative optimization method with a newly defined contribution score measure to facilitate active and inactive client determination. We empirically evaluate the communication efficiency of FL frameworks with extensive experiments on three benchmark datasets under both IID and non-IID settings. Numerical results demonstrate the outperformance of the porposed FedCliP framework over state-of-the-art FL frameworks, i.e., FedCliP can save 70% of communication overhead with only 0.2% accuracy loss on MNIST datasets, and save 50% and 15% of communication overheads with less than 1% accuracy loss on FMNIST and CIFAR-10 datasets, respectively.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 37 references that are in the map. First posted on arXiv 17 Jan 2023.
Builds on
27 of 37 references.
References · 27
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2018Federated Optimization in Heterogeneous Networkscited by 2,987
- 2020Ensemble Distillation for Robust Model Fusion in Federated Learningcited by 682
- 2020Ditto: Fair and Robust Federated Learning Through Personalizationcited by 672
- 2021FedBN: Federated Learning on Non-IID Features via Local Batch Normalizationcited by 571
- 2019Federated Learning with Personalization Layerscited by 541
- 2018Sparsified SGD with Memorycited by 376
- 2020Think Locally, Act Globally: Federated Learning with Local and Global Representationscited by 325
- 2019Model Pruning Enables Efficient Federated Learning on Edge Devicescited by 222
- 2021Personalized Federated Learning using Hypernetworkscited by 212
- 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
15 more
- 2021FedKD: Communication Efficient Federated Learning via Knowledge Distillationcited by 187
- 2021FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learningcited by 141
- 2019Overcoming Forgetting in Federated Learning on Non-IID Datacited by 120
- 2019Active Federated Learningcited by 63
- 2021Deep Gaussian Scale Mixture Prior for Spectral Compressive Imagingcited by 58
- 2022Advancing Model Pruning via Bi-level Optimizationcited by 56
- 2021Adapt to Adaptation: Learning Personalization for Cross-Silo Federated Learningcited by 53
- 2021FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learningcited by 43
- 2021A Bayesian Federated Learning Framework with Online Laplace Approximationcited by 41
- 2022Prospect Pruning: Finding Trainable Weights at Initialization using Meta-Gradientscited by 34
- 2022Acceleration of Federated Learning with Alleviated Forgetting in Local Trainingcited by 29
- 2021ProgFed: Effective, Communication, and Computation Efficient Federated Learning by Progressive Trainingcited by 27
- 2022Fast Composite Optimization and Statistical Recovery in Federated Learningcited by 12
- 2020Hyper RPCA: Joint Maximum Correntropy Criterion and Laplacian Scale Mixture Modeling On-the-Fly for Moving Object Detectioncited by 5
- 2021Searching Efficient Model-guided Deep Network for Image Denoisingcited by 2
Built on by
Not cited yet.