Dynamic Scheduling for Federated Edge Learning with Streaming Data

2023/05/02 by Hu, Chung-Hsuan, Chen, Zheng, Larsson, Erik G.
#Distributed #FOS: Computer and information sciences #Information Theory (cs.IT) #Machine Learning (cs.LG) #Networking and Internet Architecture (cs.NI) #Parallel #and Cluster Computing (cs.DC)

paper · doi:10.48550/arxiv.2305.01238

Abstract

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 resources and latency requirements, only a subset of devices is scheduled for participating in the local training process in every iteration. We formulate a stochastic network optimization problem for designing a dynamic scheduling policy that maximizes the time-average data importance from scheduled user sets subject to energy consumption and latency constraints. Our proposed algorithm based on the Lyapunov optimization framework outperforms alternative methods without considering time-varying data importance, especially when the generation of training data shows strong temporal correlation.

Related

• Dynamic Scheduling for Over-the-Air Federated Edge Learning with Energy Constraints
• Data-Aware Device Scheduling for Federated Edge Learning
• Federated Edge Learning : Design Issues and Challenges
• Scheduling for Cellular Federated Edge Learning with Importance and Channel Awareness
• Gradient and Channel Aware Dynamic Scheduling for Over-the-Air Computation in Federated Edge Learning Systems