Federated Learning in Unreliable and Resource-Constrained Cellular Wireless Networks

2020-12-09 · Mohammad Salehi, Ekram Hossain

With growth in the number of smart devices and advancements in their hardware, in recent years, data-driven machine learning techniques have drawn significant attention. However, due to privacy and communication issues, it is not possible to collect this data at a centralized location. Federated learning is a machine learning setting where the centralized location trains a learning model over remote devices. Federated learning algorithms cannot be employed in the real world scenarios unless they consider unreliable and resource-constrained nature of the wireless medium. In this paper, we propose a federated learning algorithm that is suitable for cellular wireless networks. We prove its convergence, and provide the optimal scheduling policy that maximizes the convergence rate. We also study the effect of local computation steps and communication steps on the convergence of the proposed algorithm. We prove, in practice, federated learning algorithms may solve a different problem than the one that they have been employed for if the unreliability of wireless channels is neglected. Finally, through numerous experiments on real and synthetic datasets, we demonstrate the convergence of our proposed algorithm.

📄 PDF Abstract BibTeX arXiv:2012.05137

Code (1)

mhdslh/Federated-Learning-in-Unreliable-and-Resource-Constrained-Cellular-Wireless-Networks 공식 구현 pytorch

Tasks

BIG-bench Machine Learning Federated LearningScheduling

Semantic-Aware Collaborative Deep Reinforcement Learning Over Wireless Cellular Networks

2021-11-23 · Fatemeh Lotfi, Omid Semiari, Walid Saad

Collaborative deep reinforcement learning (CDRL) algorithms in which multiple agents can coordinate over a wireless network is a promising approach to enable future intelligent and autonomous systems that rely on real-ti…

Decision Making Deep Reinforcement Learning reinforcement-learning Reinforcement Learning+1

Robust Federated Learning in Unreliable Wireless Networks: A Client Selection Approach

2025-02-24 · Yanmeng Wang, Wenkai Ji, Jian Zhou, Fu Xiao 외

Federated learning (FL) has emerged as a promising distributed learning paradigm for training deep neural networks (DNNs) at the wireless edge, but its performance can be severely hindered by unreliable wireless transmis…

Federated Learning Scheduling

Resilient Decentralized Wireless Federated Learning via Gradient Tracking with AdamW

2026-08-26 · Nguyen Van Thieu, Ti Ti Nguyen, Ons Aouedi, Vu Nguyen Ha 외 arxiv

Wireless Internet-of-Things (IoT) edge networks require decentralized learning (DecL) methods that can operate reliably under both heterogeneous local data and communication-constrained wireless links. However, existing …

Federated Learning

Prioritizing Gradient Sign Over Modulus: An Importance-Aware Framework for Wireless Federated Learning

2026-03-11 · Yiyang Yue, Jiacheng Yao, Wei Xu, Zhaohui Yang 외 arxiv

Wireless federated learning (FL) facilitates collaborative training of artificial intelligence (AI) models to support ubiquitous intelligent applications at the wireless edge. However, the inherent constraints of limited…

Federated Learning

Energy-Efficient Federated Learning for Edge Real-Time Vision via Joint Data, Computation, and Communication Design

2025-08-03 · Xiangwang Hou, Jingjing Wang, Fangming Guan, Jun Du 외 arxiv

Emerging real-time computer vision (CV) applications on wireless edge devices demand energy-efficient and privacy-preserving learning. Federated learning (FL) enables on-device training without raw data sharing, yet rema…

Federated Learning Data Augmentation