🤖 AI Summary
Federated learning (FL) addresses the tension between data privacy and distributed collaboration but faces core challenges including non-IID data distributions, system heterogeneity, high communication overhead, and insufficient privacy guarantees. This paper systematically surveys FL’s architectural design, lifecycle management, communication protocols, and key techniques—such as differential privacy, secure aggregation, model compression, personalization, and non-IID optimization—while tracing its dual paradigm evolution across cross-device and cross-silo settings. It introduces, for the first time, a comprehensive taxonomy of FL evaluation metrics and benchmark datasets. Furthermore, it proposes novel research directions integrating personalized FL with reinforcement learning and quantum computing. The work establishes a holistic knowledge graph spanning theory, algorithms, systems, and applications, and explicitly identifies six open problems. Collectively, these contributions provide a methodological foundation for building scalable, robust, and verifiable federated intelligent systems.
📝 Abstract
Federated Learning (FL) has emerged as a transformative paradigm in the field of distributed machine learning, enabling multiple clients such as mobile devices, edge nodes, or organizations to collaboratively train a shared global model without the need to centralize sensitive data. This decentralized approach addresses growing concerns around data privacy, security, and regulatory compliance, making it particularly attractive in domains such as healthcare, finance, and smart IoT systems. This survey provides a concise yet comprehensive overview of Federated Learning, beginning with its core architecture and communication protocol. We discuss the standard FL lifecycle, including local training, model aggregation, and global updates. A particular emphasis is placed on key technical challenges such as handling non-IID (non-independent and identically distributed) data, mitigating system and hardware heterogeneity, reducing communication overhead, and ensuring privacy through mechanisms like differential privacy and secure aggregation. Furthermore, we examine emerging trends in FL research, including personalized FL, cross-device versus cross-silo settings, and integration with other paradigms such as reinforcement learning and quantum computing. We also highlight real-world applications and summarize benchmark datasets and evaluation metrics commonly used in FL research. Finally, we outline open research problems and future directions to guide the development of scalable, efficient, and trustworthy FL systems.