CRS-FL: Conditional Random Sampling for Communication-Efficient and Privacy-Preserving Federated Learning
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL), a privacy-oriented distributed ML paradigm, is being gaining great interest in Internet of Things because of its capability to protect participants data privacy. Studies have been conducted to address challenges existing in standard FL, including communication efficiency and privacy-preserving. But they cannot achieve the goal of making a tradeoff between communication efficiency and model accuracy while guaranteeing privacy. This paper proposes a Conditional Random Sampling (CRS) method and implements it into the standard FL settings (CRS-FL) to tackle the above-mentioned challenges. CRS explores a stochastic coefficient based on Poisson sampling to achieve a higher probability of obtaining zero-gradient unbiasedly, and then decreases the communication overhead effectively without model accuracy degradation. Moreover, we dig out the relaxation Local Differential Privacy (LDP) guarantee conditions of CRS theoretically. Extensive experiment results indicate that (1) in communication efficiency, CRS-FL performs better than the existing methods in metric accuracy per transmission byte without model accuracy reduction in more than 7% sampling ratio (# sampling size / # model size); (2) in privacy-preserving, CRS-FL achieves no accuracy reduction compared with LDP baselines while holding the efficiency, even exceeding them in model accuracy under more sampling ratio conditions.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 25 of its 53 references that are in the map. First posted on arXiv 1 Jun 2023.
Builds on
25 of 53 references.
References · 25
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
- 2019Deep Leakage from Gradientscited by 1,021
- 2018LEAF: A Benchmark for Federated Settingscited by 792
- 2019Federated Learning with Differential Privacy: Algorithms and Performance Analysiscited by 536
- 2017Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Trainingcited by 478
- 2021Data-Free Knowledge Distillation for Heterogeneous Federated Learningcited by 383
- 2018Sparsified SGD with Memorycited by 376
- 2017Gradient Sparsification for Communication-Efficient Distributed Optimizationcited by 201
- 2019A Survey on Distributed Machine Learningcited by 188
- 2020FetchSGD: Communication-Efficient Federated Learning with Sketchingcited by 179
- 2016Concentrated Differential Privacycited by 144
13 more
- 2021Distributed Learning in Wireless Networks: Recent Progress and Future Challengescited by 129
- 2020Ternary Compression for Communication-Efficient Federated Learningcited by 57
- 2021Federated Dropout -- A Simple Approach for Enabling Federated Learning on Resource Constrained Devicescited by 56
- 2021SparseFed: Mitigating Model Poisoning Attacks in Federated Learning with Sparsificationcited by 46
- 2022Federated Learning via Inexact ADMMcited by 44
- 2020Inexact-ADMM Based Federated Meta-Learning for Fast and Continual Edge Learningcited by 22
- 2022One-shot Federated Learning without Server-side Trainingcited by 20
- 2021Differential Privacy Meets Federated Learning under Communication Constraintscited by 16
- 2021Communication-Efficient Federated Learning with Binary Neural Networkscited by 14
- 2021Faithful Edge Federated Learning: Scalability and Privacycited by 13
- 2020A Survey on Big Data for Network Traffic Monitoring and Analysiscited by 9
- 2021Sample and Threshold Differential Privacy: Histograms and applicationscited by 5
- 2023Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMMcited by 3
Built on by
Not cited yet.