Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks

• URL: http://arxiv.org/abs/2404.13804v1
• Date: Mon, 22 Apr 2024 00:16:18 GMT
• Title: Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks
• Authors: Bing Luo, Wenli Xiao, Shiqiang Wang, Jianwei Huang, Leandros Tassiulas,
• Abstract summary: Federated learning (FL) algorithms sample a fraction of clients in each round (partial participation) when the number of participants is large. Recent convergence analysis of FL have focused on slow-clock convergence due to client heterogeneity. We propose a new tractable convergence system for FL with arbitrary probability sampling.
• Score: 27.545199007002577
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Federated learning (FL) algorithms usually sample a fraction of clients in each round (partial participation) when the number of participants is large and the server's communication bandwidth is limited. Recent works on the convergence analysis of FL have focused on unbiased client sampling, e.g., sampling uniformly at random, which suffers from slow wall-clock time for convergence due to high degrees of system heterogeneity and statistical heterogeneity. This paper aims to design an adaptive client sampling algorithm for FL over wireless networks that tackles both system and statistical heterogeneity to minimize the wall-clock convergence time. We obtain a new tractable convergence bound for FL algorithms with arbitrary client sampling probability. Based on the bound, we analytically establish the relationship between the total learning time and sampling probability with an adaptive bandwidth allocation scheme, which results in a non-convex optimization problem. We design an efficient algorithm for learning the unknown parameters in the convergence bound and develop a low-complexity algorithm to approximately solve the non-convex problem. Our solution reveals the impact of system and statistical heterogeneity parameters on the optimal client sampling design. Moreover, our solution shows that as the number of sampled clients increases, the total convergence time first decreases and then increases because a larger sampling number reduces the number of rounds for convergence but results in a longer expected time per-round due to limited wireless bandwidth. Experimental results from both hardware prototype and simulation demonstrate that our proposed sampling scheme significantly reduces the convergence time compared to several baseline sampling schemes.

Related papers

• Random Aggregate Beamforming for Over-the-Air Federated Learning in Large-Scale Networks [66.18765335695414]
  We consider a joint device selection and aggregate beamforming design with the objectives of minimizing the aggregate error and maximizing the number of selected devices. To tackle the problems in a cost-effective manner, we propose a random aggregate beamforming-based scheme. We additionally use analysis to study the obtained aggregate error and the number of the selected devices when the number of devices becomes large.
  arXiv  Detail & Related papers  (2024-02-20T23:59:45Z)
• Adaptive Federated Learning in Heterogeneous Wireless Networks with Independent Sampling [15.027267764009052]
  Federated Learning (FL) algorithms sample a random subset of clients to address the straggler issue and improve communication efficiency. Recent have proposed various client sampling methods, but they have limitations in joint system and data heterogeneity. We propose a new independent client sampling strategy to minimize the wall-clock time of FL.
  arXiv  Detail & Related papers  (2024-02-15T16:51:38Z)
• Client Orchestration and Cost-Efficient Joint Optimization for NOMA-Enabled Hierarchical Federated Learning [55.49099125128281]
  We propose a non-orthogonal multiple access (NOMA) enabled HFL system under semi-synchronous cloud model aggregation. We show that the proposed scheme outperforms the considered benchmarks regarding HFL performance improvement and total cost reduction.
  arXiv  Detail & Related papers  (2023-11-03T13:34:44Z)
• Enhanced Federated Optimization: Adaptive Unbiased Client Sampling with Reduced Variance [37.646655530394604]
  Federated Learning (FL) is a distributed learning paradigm to train a global model across multiple devices without collecting local data. We present the first adaptive client sampler, K-Vib, employing an independent sampling procedure. K-Vib achieves a linear speed-up on the regret bound $tildemathcalObig(Nfrac13Tfrac23/Kfrac43big)$ within a set communication budget.
  arXiv  Detail & Related papers  (2023-10-04T10:08:01Z)
• Gradient Sparsification for Efficient Wireless Federated Learning with Differential Privacy [25.763777765222358]
  Federated learning (FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. As the model size grows, the training latency due to limited transmission bandwidth and private information degrades while using differential privacy (DP) protection. We propose sparsification empowered FL framework wireless channels, in over to improve training efficiency without sacrificing convergence performance.
  arXiv  Detail & Related papers  (2023-04-09T05:21:15Z)
• Faster Adaptive Federated Learning [84.38913517122619]
  Federated learning has attracted increasing attention with the emergence of distributed data. In this paper, we propose an efficient adaptive algorithm (i.e., FAFED) based on momentum-based variance reduced technique in cross-silo FL.
  arXiv  Detail & Related papers  (2022-12-02T05:07:50Z)
• Green, Quantized Federated Learning over Wireless Networks: An Energy-Efficient Design [68.86220939532373]
  The finite precision level is captured through the use of quantized neural networks (QNNs) that quantize weights and activations in fixed-precision format. The proposed FL framework can reduce energy consumption until convergence by up to 70% compared to a baseline FL algorithm.
  arXiv  Detail & Related papers  (2022-07-19T16:37:24Z)
• Super-resolution GANs of randomly-seeded fields [68.8204255655161]
  We propose a novel super-resolution generative adversarial network (GAN) framework to estimate field quantities from random sparse sensors. The algorithm exploits random sampling to provide incomplete views of the high-resolution underlying distributions. The proposed technique is tested on synthetic databases of fluid flow simulations, ocean surface temperature distributions measurements, and particle image velocimetry data.
  arXiv  Detail & Related papers  (2022-02-23T18:57:53Z)
• Adaptive Client Sampling in Federated Learning via Online Learning with Bandit Feedback [36.05851452151107]
  federated learning (FL) systems need to sample a subset of clients that are involved in each round of training. Despite its importance, there is limited work on how to sample clients effectively. We show how our sampling method can improve the convergence speed of optimization algorithms.
  arXiv  Detail & Related papers  (2021-12-28T23:50:52Z)
• Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Sampling [34.187387951367526]
  Federated learning (FL) algorithms usually sample a fraction in each (partial participation) when the number of participants is large. Recent works have focused on the convergence analysis of FL. We obtain new convergence bound for FL algorithms with arbitrary client sampling probabilities.
  arXiv  Detail & Related papers  (2021-12-21T14:28:40Z)
• Straggler-Resilient Federated Learning: Leveraging the Interplay Between Statistical Accuracy and System Heterogeneity [57.275753974812666]
  Federated learning involves learning from data samples distributed across a network of clients while the data remains local. In this paper, we propose a novel straggler-resilient federated learning method that incorporates statistical characteristics of the clients' data to adaptively select the clients in order to speed up the learning procedure.
  arXiv  Detail & Related papers  (2020-12-28T19:21:14Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.