How Robust is Federated Learning to Communication Error? A Comparison Study Between Uplink and Downlink Channels
Not on the map. Why?
Abstract (arXiv)
Because of its privacy-preserving capability, federated learning (FL) has attracted significant attention from both academia and industry. However, when being implemented over wireless networks, it is not clear how much communication error can be tolerated by FL. This paper investigates the robustness of FL to the uplink and downlink communication error. Our theoretical analysis reveals that the robustness depends on two critical parameters, namely the number of clients and the numerical range of model parameters. It is also shown that the uplink communication in FL can tolerate a higher bit error rate (BER) than downlink communication, and this difference is quantified by a proposed formula. The findings and theoretical analyses are further validated by extensive experiments.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 16 of its 22 references that are in the map. First posted on arXiv 25 Oct 2023.
Builds on
16 of 22 references.
References · 16
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
- 2018Federated Optimization in Heterogeneous Networkscited by 2,971
- 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
- 2016Federated Learning: Strategies for Improving Communication Efficiencycited by 1,461
- 2019FedPAQ: A Communication-Efficient Federated Learning Method with Periodic Averaging and Quantizationcited by 349
- 2018Federated Learning via Over-the-Air Computationcited by 215
- 2016Distributed Mean Estimation with Limited Communicationcited by 134
- 2020Adaptive Gradient Sparsification for Efficient Federated Learning: An Online Learning Approachcited by 80
- 2020Over-the-Air Federated Learning from Heterogeneous Datacited by 72
- 2020Federated Learning With Quantized Global Model Updatescited by 54
- 2019Robust Federated Learning with Noisy Communicationcited by 33
4 more
- 2020Convergence of Federated Learning over a Noisy Downlinkcited by 29
- 2021Time-Correlated Sparsification for Communication-Efficient Federated Learningcited by 25
- 2020Fast Convergence Algorithm for Analog Federated Learningcited by 16
- 2020Cluster-Based Cooperative Digital Over-the-Air Aggregation for Wireless Federated Edge Learningcited by 6
Built on by
Citing papers per year: 2024: 1; 2025: 1.
2 papers.