Loss Tolerant Federated Learning

2021/05/08 by Pengyuan Zhou, Zhou, Pengyuan, Pei Fang +3 · 8 citations
Computer Science · #Age of Information Optimization #Artificial Intelligence (cs.AI) #Bandwidth (computing) #Computer network #Computer science #Distributed computing #FOS: Computer and information sciences #Federated learning #IoT and Edge/Fog Computing #Machine Learning (cs.LG) #Machine learning #Network packet #Networking and Internet Architecture (cs.NI) #Packet loss #Personalization #Privacy-Preserving Technologies in Data #Selection (genetic algorithm) #Upload #World Wide Web #cs.AI #cs.LG #cs.NI

paper · pdf · doi:10.48550/arxiv.2105.03591

published in arXiv (Cornell University) (Cornell University)

arxiv created 2021/05/08 · openalex publication_date 2021/05/08 · arxiv updated 2021/05/11 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/08

Abstract

Federated learning has attracted attention in recent years for collaboratively training data on distributed devices with privacy-preservation. The limited network capacity of mobile and IoT devices has been seen as one of the major challenges for cross-device federated learning. Recent solutions have been focusing on threshold-based client selection schemes to guarantee the communication efficiency. However, we find this approach can cause biased client selection and results in deteriorated performance. Moreover, we find that the challenge of network limit may be overstated in some cases and the packet loss is not always harmful. In this paper, we explore the loss tolerant federated learning (LT-FL) in terms of aggregation, fairness, and personalization. We use ThrowRightAway (TRA) to accelerate the data uploading for low-bandwidth-devices by intentionally ignoring some packet losses. The results suggest that, with proper integration, TRA and other algorithms can together guarantee the personalization and fairness performance in the face of packet loss below a certain fraction (10%-30%).

Citations

• Federated Learning: Strategies for Improving Communication Efficiency
• Towards Federated Learning at Scale: System Design
• Fair Resource Allocation in Federated Learning
• Personalized Federated Learning: A Meta-Learning Approach
• Federated Learning in Mobile Edge Networks: A Comprehensive Survey
• Collaborative Fairness in Federated Learning

Cited by

• Fairness in Federated Learning: Trends, Challenges, and Opportunities

Related

• FTTE: Enabling Federated and Resource-Constrained Deep Edge Intelligence
• FedAdapt: Adaptive Offloading for IoT Devices in Federated Learning
• Utility Fairness for the Differentially Private Federated Learning
• To Store or Not? Online Data Selection for Federated Learning with Limited Storage
• Constrained Differentially Private Federated Learning for Low-bandwidth Devices