A Joint Learning and Communications Framework for Federated Learning over Wireless Networks

Abstract

In this paper, the problem of training federated learning (FL) algorithms over a realistic wireless network is studied. In particular, in the considered model, wireless users execute an FL algorithm while training their local FL models using their own data and transmitting the trained local FL models to a base station (BS) that will generate a global FL model and send it back to the users. Since all training parameters are transmitted over wireless links, the quality of the training will be affected by wireless factors such as packet errors and the availability of wireless resources. Meanwhile, due to the limited wireless bandwidth, the BS must select an appropriate subset of users to execute the FL algorithm so as to build a global FL model accurately. This joint learning, wireless resource allocation, and user selection problem is formulated as an optimization problem whose goal is to minimize an FL loss function that captures the performance of the FL algorithm. To address this problem, a closed-form expression for the expected convergence rate of the FL algorithm is first derived to quantify the impact of wireless factors on FL. Then, based on the expected convergence rate of the FL algorithm, the optimal transmit power for each user is derived, under a given user selection and uplink resource block (RB) allocation scheme. Finally, the user selection and uplink RB allocation is optimized so as to minimize the FL loss function. Simulation results show that the proposed joint federated learning and communication framework can reduce the FL loss function value by up to 10% and 16%, respectively, compared to: 1) An optimal user selection algorithm with random resource allocation and 2) a standard FL algorithm with random user selection and resource allocation.

This paper has been accepted by IEEE Transactions on Wireless Communications. Our code is available at: https://github.com/mzchen0/Wireless-FL

References in corpus (4)

• Federated Optimization: Distributed Machine Learning for On-Device Intelligence
• Energy-Efficient Radio Resource Allocation for Federated Edge Learning
• Convergence Time Optimization for Federated Learning over Wireless Networks
• Multi-hop Federated Private Data Augmentation with Sample Compression

Cited by in corpus (30)

• Multi-Armed Bandit Based Client Scheduling for Federated Learning
• UVeQFed: Universal Vector Quantization for Federated Learning
• Resource Management in Wireless Networks via Multi-Agent Deep Reinforcement Learning
• Multi-Stage Hybrid Federated Learning over Large-Scale D2D-Enabled Fog Networks
• 6G White Paper on Machine Learning in Wireless Communication Networks
• Reflections in the Sky: Joint Trajectory and Passive Beamforming Design for Secure UAV Networks with Reconfigurable Intelligent Surface
• Energy-Efficient Wireless Communications with Distributed Reconfigurable Intelligent Surfaces
• Delay Minimization for Federated Learning Over Wireless Communication Networks
• Communication Efficient Federated Learning over Multiple Access Channels
• Bayesian Federated Learning over Wireless Networks
• Federated Learning in the Sky: Joint Power Allocation and Scheduling with UAV Swarms
• Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning
• Communication-Efficient Robust Federated Learning Over Heterogeneous Datasets
• Wireless Communications for Collaborative Federated Learning
• Wireless for Machine Learning
• Decentralized Federated Learning via SGD over Wireless D2D Networks
• Blockchain Assisted Decentralized Federated Learning (BLADE-FL) with Lazy Clients
• Energy-Efficient Resource Management for Federated Edge Learning with CPU-GPU Heterogeneous Computing
• Prophet: Proactive Candidate-Selection for Federated Learning by Predicting the Qualities of Training and Reporting Phases
• MAB-based Client Selection for Federated Learning with Uncertain Resources in Mobile Networks
• Machine Learning for Predictive Deployment of UAVs with Multiple Access
• Linear Regression over Networks with Communication Guarantees
• Task Allocation for Asynchronous Mobile Edge Learning with Delay and Energy Constraints
• Channel Assignment in Uplink Wireless Communication using Machine Learning Approach
• Meta-Reinforcement Learning for Trajectory Design in Wireless UAV Networks
• UAV-assisted Online Machine Learning over Multi-Tiered Networks: A Hierarchical Nested Personalized Federated Learning Approach
• Integrated user scheduling and beam steering in over-the-air federated learning for mobile IoT
• Wireless Distributed Edge Learning: How Many Edge Devices Do We Need?
• Jointly Optimizing Dataset Size and Local Updates in Heterogeneous Mobile Edge Learning
• Energy-aware Resource Management for Federated Learning in Multi-access Edge Computing Systems