Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling
Not on the map. Why?
Abstract (arXiv)
Federated Learning (FL) algorithms commonly sample a random subset of clients to address the straggler issue and improve communication efficiency. While recent works have proposed various client sampling methods, they have limitations in joint system and data heterogeneity design, which may not align with practical heterogeneous wireless networks. In this work, we advocate a new independent client sampling strategy to minimize the wall-clock training time of FL, while considering data heterogeneity and system heterogeneity in both communication and computation. We first derive a new convergence bound for non-convex loss functions with independent client sampling and then propose an adaptive bandwidth allocation scheme. Furthermore, we propose an efficient independent client sampling algorithm based on the upper bounds on the convergence rounds and the expected per-round training time, to minimize the wall-clock time of FL, while considering both the data and system heterogeneity. Experimental results under practical wireless network settings with real-world prototype demonstrate that the proposed independent sampling scheme substantially outperforms the current best sampling schemes under various training models and datasets.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 16 of its 21 references that are in the map. First posted on arXiv 15 Feb 2024.
Builds on
16 of 21 references.
References · 16
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
- 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
- 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
- 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 347
- 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 192
- 2019On the Convergence of Local Descent Methods in Federated Learningcited by 150
- 2020Optimal Client Sampling for Federated Learningcited by 123
- 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
- 2020Cost-Effective Federated Learning Designcited by 61
- 2022A Unified Analysis of Federated Learning with Arbitrary Client Participationcited by 45
- 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
- 2020Federated Learning under Importance Samplingcited by 26
4 more
- 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
- 2019Federated Learning for Ranking Browser History Suggestionscited by 23
- 2022Federated Learning with Flexible Controlcited by 12
- 2023Optimization Design for Federated Learning in Heterogeneous 6G Networkscited by 7
Built on by
Citing papers per year: 2026: 1.
1 paper.