From Distributed Machine Learning to Federated Learning: A Survey
arXiv:2104.14362 · doi:10.1007/s10115-022-01664-x
Abstract
In recent years, data and computing resources are typically distributed in the devices of end users, various regions or organizations. Because of laws or regulations, the distributed data and computing resources cannot be directly shared among different regions or organizations for machine learning tasks. Federated learning emerges as an efficient approach to exploit distributed data and computing resources, so as to collaboratively train machine learning models, while obeying the laws and regulations and ensuring data security and data privacy. In this paper, we provide a comprehensive survey of existing works for federated learning. We propose a functional architecture of federated learning systems and a taxonomy of related techniques. Furthermore, we present the distributed training, data communication, and security of FL systems. Finally, we analyze their limitations and propose future research directions.
Accepted by KAIS
References in corpus (58)
- Deep Learning with Differential Privacy
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Federated Learning: Challenges, Methods, and Future Directions
- Federated Learning: Strategies for Improving Communication Efficiency
- A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection
- A Survey on Multi-view Learning
- A Survey on Distributed Machine Learning
- Robust Aggregation for Federated Learning
- How To Backdoor Federated Learning
- Learning Differentially Private Recurrent Language Models
- Diffusion Adaptation Strategies for Distributed Optimization and Learning over Networks
- Communication-Efficient Federated Deep Learning with Asynchronous Model Update and Temporally Weighted Aggregation
- Federated Learning with Personalization Layers
- Differentially Private Federated Learning: A Client Level Perspective
- Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption
- iDLG: Improved Deep Leakage from Gradients
- Can You Really Backdoor Federated Learning?
- Mitigating Sybils in Federated Learning Poisoning
- Fair Resource Allocation in Federated Learning
- Adaptive Personalized Federated Learning
- A generic framework for privacy preserving deep learning
- FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
- LEAF: A Benchmark for Federated Settings
- UVeQFed: Universal Vector Quantization for Federated Learning
- Agnostic Federated Learning
- Threats to Federated Learning: A Survey
- Sparsified SGD with Memory
- Personalized Federated Learning with Moreau Envelopes
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Byzantine-Robust Federated Machine Learning through Adaptive Model Averaging
- Expanding the Reach of Federated Learning by Reducing Client Resource Requirements
- Analysis and Optimal Edge Assignment For Hierarchical Federated Learning on Non-IID Data
- Error Feedback Fixes SignSGD and other Gradient Compression Schemes
- Bayesian Nonparametric Federated Learning of Neural Networks
- Peer-to-peer Federated Learning on Graphs
- Federated Learning for Internet of Things: A Federated Learning Framework for On-device Anomaly Data Detection
- Abnormal Client Behavior Detection in Federated Learning
- Flower: A Friendly Federated Learning Research Framework
- Federated Learning with Matched Averaging
- PrivFL: Practical Privacy-preserving Federated Regressions on High-dimensional Data over Mobile Networks
- Multi-Participant Multi-Class Vertical Federated Learning
- Free-riders in Federated Learning: Attacks and Defenses
- A Communication Efficient Collaborative Learning Framework for Distributed Features
- Secure Byzantine-Robust Machine Learning
- Distributed TensorFlow with MPI
- GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
- Hierarchical Federated Learning through LAN-WAN Orchestration
- Federated Learning Meets Multi-objective Optimization
- Federated Learning with Compression: Unified Analysis and Sharp Guarantees
- Scalable Differential Privacy with Certified Robustness in Adversarial Learning
- Backdoor Attacks on Federated Meta-Learning
- Interpret Federated Learning with Shapley Values
- Communication-efficient distributed SGD with Sketching
- Quantification of the Leakage in Federated Learning
- Secure Multi-Party Computation Based Privacy Preserving Extreme Learning Machine Algorithm Over Vertically Distributed Data
- Differentially Private Federated Learning with Laplacian Smoothing
- Compressing Gradient Optimizers via Count-Sketches
- Policy-Based Federated Learning