paper-with-me

Papers

Federated Learning over Noisy Channels: Convergence Analysis and Design Examples

2021-01-06 · Xizixiang Wei, Cong Shen

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 these practically important questions by explicitly incorporating both uplink and downlink noisy channels in the FL pipeline. We present several novel convergence analyses of FL over simultaneous uplink and downlink noisy communication channels, which encompass full and partial clients participation, direct model and model differential transmissions, and non-independent and identically distributed (IID) local datasets. These analyses characterize the sufficient conditions for FL over noisy channels to have the same convergence behavior as the ideal case of no communication error. More specifically, in order to maintain the O(1/T) convergence rate of FedAvg with perfect communications, the uplink and downlink signal-to-noise ratio (SNR) for direct model transmissions should be controlled such that they scale as O(t^2) where t is the index of communication rounds, but can stay constant for model differential transmissions. The key insight of these theoretical results is a "flying under the radar" principle - stochastic gradient descent (SGD) is an inherent noisy process and uplink/downlink communication noises can be tolerated as long as they do not dominate the time-varying SGD noise. We exemplify these theoretical findings with two widely adopted communication techniques - transmit power control and diversity combining - and further validating their performance advantages over the standard methods via extensive numerical experiments using several real-world FL tasks.

📄 PDF Abstract BibTeX arXiv:2101.02198

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

SGD Stochastic Gradient Descent is an iterative optimization technique that uses minibatches of data to form an expectation of the gradient, rather than the full gradient using…

Similar Papers 제목 키워드 기반

Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channels

2023-10-25 · Zheshun Wu, Zenglin Xu, Hongfang Yu, Jie Liu

With the rapid growth of edge intelligence, the deployment of federated learning (FL) over wireless networks has garnered increasing attention, which is called Federated Edge Learning (FEEL). In FEEL, both mobile devices…

Federated Learning

On the Convergence of Decentralized Federated Learning Under Imperfect Information Sharing

2023-03-19 · Vishnu Pandi Chellapandi, Antesh Upadhyay, Abolfazl Hashemi, Stanislaw H /. Zak

Decentralized learning and optimization is a central problem in control that encompasses several existing and emerging applications, such as federated learning. While there exists a vast literature on this topic and most…

Distributed OptimizationFederated Learning

FedNMUT -- Federated Noisy Model Update Tracking Convergence Analysis

2024-03-20 · Vishnu Pandi Chellapandi, Antesh Upadhyay, Abolfazl Hashemi, Stanislaw H. Żak

A novel Decentralized Noisy Model Update Tracking Federated Learning algorithm (FedNMUT) is proposed that is tailored to function efficiently in the presence of noisy communication channels that reflect imperfect informa…

Federated Learningmodel

Communication-Efficient Federated Learning over Wireless Channels via Gradient Sketching

2024-10-30 · Vineet Sunil Gattani, Junshan Zhang, Gautam Dasarathy

Large-scale federated learning (FL) over wireless multiple access channels (MACs) has emerged as a crucial learning paradigm with a wide range of applications. However, its widespread adoption is hindered by several majo…

Federated Learning

Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning

2020-07-03 · Anis Elgabli, Jihong Park, Chaouki Ben Issaid, Mehdi Bennis

Wireless connectivity is instrumental in enabling scalable federated learning (FL), yet wireless channels bring challenges for model training, in which channel randomness perturbs each worker's model update while multipl…

Federated LearningPrivacy Preserving