On-Demand Model and Client Deployment in Federated Learning with Deep Reinforcement Learning
On the map: Deep reinforcement learning methods → RL for energy, networks and operations
Abstract (arXiv)
In Federated Learning (FL), the limited accessibility of data from diverse locations and user types poses a significant challenge due to restricted user participation. Expanding client access and diversifying data enhance models by incorporating diverse perspectives, thereby enhancing adaptability. However, challenges arise in dynamic and mobile environments where certain devices may become inaccessible as FL clients, impacting data availability and client selection methods. To address this, we propose an On-Demand solution, deploying new clients using Docker Containers on-the-fly. Our On-Demand solution, employing Deep Reinforcement Learning (DRL), targets client availability and selection, while considering data shifts, and container deployment complexities. It employs an autonomous end-to-end solution for handling model deployment and client selection. The DRL strategy uses a Markov Decision Process (MDP) framework, with a Master Learner and a Joiner Learner. The designed cost functions represent the complexity of the dynamic client deployment and selection. Simulated tests show that our architecture can easily adjust to changes in the environment and respond to On-Demand requests. This underscores its ability to improve client availability, capability, accuracy, and learning efficiency, surpassing heuristic and tabular reinforcement learning solutions.
Key facts. Cited by 1 paper in the map (data through 13 Oct 2026). Placed in RL for energy, networks and operations, one of 15 directions in Deep reinforcement learning methods. Builds on 19 of its 47 references that are in the map. First posted on arXiv 12 May 2024.
Builds on
19 of 47 references.
References · 19
- 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,653
- 2018Federated Optimization in Heterogeneous Networkscited by 2,981
- 2019A Joint Learning and Communications Framework for Federated Learning over Wireless Networkscited by 263
- 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 249
- 2018A Hybrid Approach to Privacy-Preserving Federated Learningcited by 210
- 2022PromptFL: Let Federated Participants Cooperatively Learn Prompts Instead of Models -- Federated Learning in Age of Foundation Modelcited by 133
- 2022Jump-Start Reinforcement Learningcited by 103
- 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 102
- 2019Decentralized Federated Learning: A Segmented Gossip Approachcited by 64
- 2021Flexible Clustered Federated Learning for Client-Level Data Distribution Shiftcited by 47
- 2020Communication-Efficient Federated Learning with Compensated Overlap-FedAvgcited by 31
- 2022Federated Learning Under Intermittent Client Availability and Time-Varying Communication Constraintscited by 30
7 more
- 2017The ALAMO approach to machine learningcited by 18
- 2022Deep Reinforcement Learning Assisted Federated Learning Algorithm for Data Management of IIoTcited by 15
- 2022ON-DEMAND-FL: A Dynamic and Efficient Multi-Criteria Federated Learning Client Deployment Schemecited by 7
- 2022FedMint: Intelligent Bilateral Client Selection in Federated Learning with Newcomer IoT Devicescited by 4
- 2022ModularFed: Leveraging Modularity in Federated Learning Frameworkscited by 4
- 2023Emergence of Adaptive Circadian Rhythms in Deep Reinforcement Learningcited by 1
- 2024Trust Driven On-Demand Scheme for Client Deployment in Federated Learningcited by 1
Built on by
Citing papers per year: 2024: 1.
1 paper.