paper-with-me

홈 › Papers

Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimization

2022-01-19 · Jake Perazzone, Shiqiang Wang, Mingyue Ji, Kevin Chan

Federated learning (FL) is a useful tool in distributed machine learning that utilizes users' local datasets in a privacy-preserving manner. When deploying FL in a constrained wireless environment; however, training models in a time-efficient manner can be a challenging task due to intermittent connectivity of devices, heterogeneous connection quality, and non-i.i.d. data. In this paper, we provide a novel convergence analysis of non-convex loss functions using FL on both i.i.d. and non-i.i.d. datasets with arbitrary device selection probabilities for each round. Then, using the derived convergence bound, we use stochastic optimization to develop a new client selection and power allocation algorithm that minimizes a function of the convergence bound and the average communication time under a transmit power constraint. We find an analytical solution to the minimization problem. One key feature of the algorithm is that knowledge of the channel statistics is not required and only the instantaneous channel state information needs to be known. Using the FEMNIST and CIFAR-10 datasets, we show through simulations that the communication time can be significantly decreased using our algorithm, compared to uniformly random participation.

📄 PDF Abstract BibTeX arXiv:2201.07912

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPrivacy PreservingSchedulingStochastic Optimization

Similar Papers 제목 키워드 기반

Dynamic Scheduling for Federated Edge Learning with Streaming Data

2023-05-02 · Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson

In this work, we consider a Federated Edge Learning (FEEL) system where training data are randomly generated over time at a set of distributed edge devices with long-term energy constraints. Due to limited communication …

Scheduling

Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach

2024-05-20 · Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson

Federated learning (FL) has received significant attention in recent years for its advantages in efficient training of machine learning models across distributed clients without disclosing user-sensitive data. Specifical…

Federated LearningScheduling

Over-the-Air Federated Averaging with Limited Power and Privacy Budgets

2023-05-05 · Na Yan, Kezhi Wang, Cunhua Pan, Kok Keong Chai 외

To jointly overcome the communication bottleneck and privacy leakage of wireless federated learning (FL), this paper studies a differentially private over-the-air federated averaging (DP-OTA-FedAvg) system with a limited…

Federated LearningScheduling

Scheduling for Cellular Federated Edge Learning with Importance and Channel Awareness

2020-04-01 · Jinke Ren, Yinghui He, Dingzhu Wen, Guanding Yu 외

In cellular federated edge learning (FEEL), multiple edge devices holding local data jointly train a neural network by communicating learning updates with an access point without exchanging their data samples. With very …

DiversityScheduling

Personalized Federated Learning by Energy-Efficient UAV Communications

2026-05-24 · Shiqian Guo, Jianqing Liu, Beatriz Lorenzo arxiv

Federated learning (FL) is an effective paradigm for enhancing the learning capability of edge devices while preserving data privacy. In geographically dispersed FL systems, such as sensor networks in remote areas, unman…

Personalized Federated Learning