Asynchronous Online Federated Learning for Edge Devices
Explore this paper's citation graph
Summary
An Asynchronous Online Federated Learning (ASO- fed) framework, where the edge devices perform online learning with continuous streaming local data and a central server aggregates model parameters from local clients is presented.
- Type
- article
- Published
- 2019-11-05
- Cited by
- 57
- References
- 46
- Access
- Open access
- OpenAlex
- https://openalex.org/W2982859792
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:207880895
Keywords
Computer science, Asynchronous communication, Edge device, Enhanced Data Rates for GSM Evolution, Dropout (neural networks)
References
- Linear Algorithms for Online Multitask Classification
- Matrix regularization techniques for online multitask learning
- Exact Soft Confidence-Weighted Learning
- An Asynchronous Distributed Proximal Gradient Method for Composite Convex Optimization
- Multi-Task Feature Learning Via Efficient l2, 1-Norm Minimization
- Large-Scale Personalized Human Activity Recognition Using Online Multitask Learning
- Collaborating between Local and Global Learning for Distributed Online Multiple Tasks
- Online learning for multi-task feature selection
- Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models
- Asynchronous distributed optimization using a randomized alternating direction method of multipliers
- On the normalization of interval and fuzzy weights
- Client–Server Multitask Learning From Distributed Datasets
- Introductory Lectures on Convex Optimization - A Basic Course
- Communication Efficient Distributed Machine Learning with the Parameter Server
- Optimal Distributed Online Prediction Using Mini-Batches
- Regularized multi--task learning
- Amortized Analysis on Asynchronous Gradient Descent
- Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanism
- Optimization Methods for Large-Scale Machine Learning
- Asynchronous Multi-task Learning
Cited by
- ELFISH: Resource-Aware Federated Learning on Heterogeneous Edge Devices
- Federated Continual Learning with Adaptive Parameter Communication
- Industrial Federated Learning - Requirements and System Design
- Towards Flexible Device Participation in Federated Learning for Non-IID Data
- Federated Semi-Supervised Learning with Inter-Client Consistency
- A Systematic Literature Review on Federated Machine Learning
- A review of applications in federated learning
- FedAT: A Communication-Efficient Federated Learning Method with Asynchronous Tiers under Non-IID Data
- Federated Continual Learning with Weighted Inter-client Transfer
- Blockchain based End-to-end Tracking System for Distributed IoT Intelligence Application Security Enhancement
- A Survey on federated learning*
- Poster: Maintaining Training Efficiency and Accuracy for Edge-assisted Online Federated Learning with ABS
- Federated vs. Centralized Machine Learning under Privacy-elastic Users: A Comparative Analysis
- Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems
- Time Efficient Federated Learning with Semi-asynchronous Communication
- A survey of federated learning for edge computing: Research problems and solutions
- Resource-Efficient Federated Learning with Hierarchical Aggregation in Edge Computing
- HySync: Hybrid Federated Learning with Effective Synchronization
- Federated Continuous Learning With Broad Network Architecture
- A Survey on Federated Learning for Resource-Constrained IoT Devices
Related papers
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Asynchronous Federated Optimization
- Federated Learning with Non-IID Data
- Towards Federated Learning at Scale: System Design
- Communication-Efficient Federated Deep Learning With Layerwise Asynchronous Model Update and Temporally Weighted Aggregation
- Federated Learning: Strategies for Improving Communication Efficiency
- Advances and Open Problems in Federated Learning