Design and Analysis of Uplink and Downlink Communications for Federated Learning
Communication has been known to be one of the primary bottlenecks of federated learning (FL), and yet existing studies have not addressed the efficient communication design, particularly in wireless FL where both uplink and downlink communications have to be considered. In this paper, we focus on the design and analysis of physical layer quantization and transmission methods for wireless FL. We answer the question of what and how to communicate between clients and the parameter server and evaluate the impact of the various quantization and transmission options of the updated model on the learning performance. We provide new convergence analysis of the well-known FedAvg under non-i.i.d. dataset distributions, partial clients participation, and finite-precision quantization in uplink and downlink communications. These analyses reveal that, in order to achieve an O(1/T) convergence rate with quantization, transmitting the weight requires increasing the quantization level at a logarithmic rate, while transmitting the weight differential can keep a constant quantization level. Comprehensive numerical evaluation on various real-world datasets reveals that the benefit of a FL-tailored uplink and downlink communication design is enormous - a carefully designed quantization and transmission achieves more than 98% of the floating-point baseline accuracy with fewer than 10% of the baseline bandwidth, for majority of the experiments on both i.i.d. and non-i.i.d. datasets. In particular, 1-bit quantization (3.1% of the floating-point baseline bandwidth) achieves 99.8% of the floating-point baseline accuracy at almost the same convergence rate on MNIST, representing the best known bandwidth-accuracy tradeoff to the best of the authors' knowledge.
Code (0)
등록된 구현이 없습니다.
Tasks
Federated LearningQuantizationSimilar Papers 제목 키워드 기반
Federated Learning over Noisy Channels: Convergence Analysis and Design Examples
Does Federated Learning (FL) work when both uplink and downlink communications have errors? How much communication noise can FL handle and what is its impact to the learning performance? This work is devoted to answering…
Federated LearningImproved Convergence Analysis and SNR Control Strategies for Federated Learning in the Presence of Noise
We propose an improved convergence analysis technique that characterizes the distributed learning paradigm of federated learning (FL) with imperfect/noisy uplink and downlink communications. Such imperfect communication …
Federated LearningBICompFL: Stochastic Federated Learning with Bi-Directional Compression
We address the prominent communication bottleneck in federated learning (FL). We specifically consider stochastic FL, in which models or compressed model updates are specified by distributions rather than deterministic p…
Federated LearningLink Budget Analysis for Free-Space Optical Satellite Networks
Free-space optical satellite networks (FSOSNs) will employ free-space optical links between satellites and between satellites and ground stations, and the link budget for optical inter-satellite links and optical uplink/…
Mix2FLD: Downlink Federated Learning After Uplink Federated Distillation With Two-Way Mixup
This letter proposes a novel communication-efficient and privacy-preserving distributed machine learning framework, coined Mix2FLD. To address uplink-downlink capacity asymmetry, local model outputs are uploaded to a ser…
Federated LearningPrivacy Preserving