Federated Machine Learning for Smart Logistics: A Comprehensive Survey

Abstract

Federated Machine Learning, or in short Federated Learning (FL), has emerged as a promising paradigm for decentralized, privacy-preserving machine learning, with significant potential in transportation and logistics. This survey provides a comprehensive review of FL applications in Smart Logistics such as supply chain optimization, warehouse management, and efficient delivery. We discuss core principles of FL, alongside challenges when applying to Smart Logistics domain. We provide a comprehensive clustering of methodologies to tackle the problem. Finally, we highlight future research directions, emphasizing the integration of FL with IoT and edge computing, personalized and adaptive models, privacy, security, and sustainability to enhance smart transportation systems.