Adaptive Biased User Scheduling for Heterogeneous Wireless Federate Learning Network

2025/05/08 by Changxiang Wu, Wu, Changxiang, Yijing Ren +5 · 1 citation
Computer Science · #Age of Information Optimization #Energy Efficient Wireless Sensor Networks #FOS: Electrical engineering #Privacy-Preserving Technologies in Data #Systems and Control (eess.SY) #electronic engineering #information engineering

paper · pdf · doi:10.48550/arxiv.2505.05231

openalex publication_date 2025/05/08 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Federated Learning (FL) has revolutionized collaborative model training in distributed networks, prioritizing data privacy and communication efficiency. This paper investigates efficient deployment of FL in wireless heterogeneous networks, focusing on strategies to accelerate convergence despite stragglers. The primary objective is to minimize long-term convergence wall-clock time through optimized user scheduling and resource allocation. While stragglers may introduce delays in a single round, their inclusion can expedite subsequent rounds, particularly when they possess critical information. Moreover, balancing single-round duration with the number of cumulative rounds, compounded by dynamic training and transmission conditions, necessitates a novel approach beyond conventional optimization solutions. To tackle these challenges, convergence analysis with respect to adaptive and biased scheduling is derived. Then, by factoring in real-time system and statistical information, including diverse energy constraints and users' energy harvesting capabilities, a deep reinforcement learning approach, empowered by proximal policy optimization, is employed to adaptively select user sets. For the scheduled users, Lagrangian decomposition is applied to optimize local resource utilization, further enhancing system efficiency. Simulation results validate the effectiveness and robustness of the proposed framework for various FL tasks, demonstrating reduced task time compared to existing benchmarks under various settings.

Citations

• Adaptive Heterogeneous Client Sampling for Federated Learning over Wireless Networks
• Client Selection in Federated Learning: Principles, Challenges, and Opportunities
• Cost-Effective Federated Learning in Mobile Edge Networks
• Mobility-Aware Cluster Federated Learning in Hierarchical Wireless Networks
• Federated Learning under Importance Sampling
• Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning
• Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspective
• Convergence Time Optimization for Federated Learning over Wireless Networks
• Energy Efficient Federated Learning Over Wireless Communication Networks
• A Joint Learning and Communications Framework for Federated Learning over Wireless Networks
• Federated Learning: Challenges, Methods, and Future Directions
• On the Convergence of FedAvg on Non-IID Data
• Federated Learning for Mobile Keyboard Prediction
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems
• Adaptive Federated Learning in Resource Constrained Edge Computing Systems
• Not All Samples Are Created Equal: Deep Learning with Importance Sampling
• Deep Reinforcement Learning for Dynamic Multichannel Access in Wireless Networks
• Proximal Policy Optimization Algorithms
• Wireless Networks with RF Energy Harvesting: A Contemporary Survey
• Stochastic Gradient Descent, Weighted Sampling, and the Randomized\n Kaczmarz algorithm

Cited by

• Computation-aware Energy-harvesting Federated Learning: Cyclic Scheduling with Selective Participation

Related

• Device Scheduling with Fast Convergence for Wireless Federated Learning
• FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks
• Scheduling Policies for Federated Learning in Wireless Networks
• Joint Device Scheduling and Resource Allocation for Latency Constrained Wireless Federated Learning
• Analysis and Optimization of Wireless Federated Learning with Data Heterogeneity