Federated Learning Survey: A Multi-Level Taxonomy of Aggregation Techniques, Experimental Insights, and Future Frontiers
arXiv:2511.22616 · doi:10.1145/3678182
Abstract
The integration of IoT and AI has unlocked innovation across industries, but growing privacy concerns and data isolation hinder progress. Traditional centralized ML struggles to overcome these challenges, which has led to the rise of Federated Learning (FL), a decentralized paradigm that enables collaborative model training without sharing local raw data. FL ensures data privacy, reduces communication overhead, and supports scalability, yet its heterogeneity adds complexity compared to centralized approaches. This survey focuses on three main FL research directions: personalization, optimization, and robustness, offering a structured classification through a hybrid methodology that combines bibliometric analysis with systematic review to identify the most influential works. We examine challenges and techniques related to heterogeneity, efficiency, security, and privacy, and provide a comprehensive overview of aggregation strategies, including architectures, synchronization methods, and diverse federation objectives. To complement this, we discuss practical evaluation approaches and present experiments comparing aggregation methods under IID and non-IID data distributions. Finally, we outline promising research directions to advance FL, aiming to guide future innovation in this rapidly evolving field.
Author-Accepted Manuscript. 65 pages, 26 figures, 20 tables. Published in ACM Transactions on Intelligent Systems and Technology (TIST), 2024
References in corpus (27)
- Federated Learning: Challenges, Methods, and Future Directions
- What should 6G be?
- Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning
- Federated Learning for Internet of Things: A Comprehensive Survey
- Towards Personalized Federated Learning
- MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification
- Federated Learning for 6G Communications: Challenges, Methods, and Future Directions
- MedMNIST Classification Decathlon: A Lightweight AutoML Benchmark for Medical Image Analysis
- Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Block Hunter: Federated Learning for Cyber Threat Hunting in Blockchain-based IIoT Networks
- Hierarchical Federated Learning with Quantization: Convergence Analysis and System Design
- Analysis and Optimal Edge Assignment For Hierarchical Federated Learning on Non-IID Data
- Scheduling and Aggregation Design for Asynchronous Federated Learning over Wireless Networks
- Joint Privacy Enhancement and Quantization in Federated Learning
- FedLab: A Flexible Federated Learning Framework
- Decentralized Deep Learning for Multi-Access Edge Computing: A Survey on Communication Efficiency and Trustworthiness
- Throughput-Optimal Topology Design for Cross-Silo Federated Learning
- FLAME: Federated Learning Across Multi-device Environments
- Federated Learning with Nesterov Accelerated Gradient
- Towards Efficient Synchronous Federated Training: A Survey on System Optimization Strategies
- STEM: A Stochastic Two-Sided Momentum Algorithm Achieving Near-Optimal Sample and Communication Complexities for Federated Learning
- Federated and Transfer Learning: A Survey on Adversaries and Defense Mechanisms
- Personalized Federated Learning with Multi-branch Architecture
- FLVoogd: Robust And Privacy Preserving Federated Learning
- Efficient and Light-Weight Federated Learning via Asynchronous Distributed Dropout
- Modular Federated Learning