Device Selection

Device selection in federated learning (FL) focuses on optimizing which devices participate in each training round to improve model accuracy, training speed, and resource efficiency. Current research emphasizes algorithms that consider device heterogeneity (varying computational resources and data distributions), employing techniques like reinforcement learning, multi-armed bandits, and imitation learning to select optimal subsets of devices. These advancements aim to address communication bottlenecks and improve the overall performance of FL systems, impacting the scalability and practicality of privacy-preserving machine learning across diverse applications like IoT networks and distributed AI.

Papers

August 26, 2024

Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network
Shunfeng Chu, Jun Li, Jianxin Wang, Yiyang Ni, Kang Wei, Wen Chen, Shi Jin
Digital Twin Internet of Thing Network Asynchronous Federated Learning Device Scheduling Device Selection

June 3, 2024

Efficient Data Distribution Estimation for Accelerated Federated Learning
Yuanli Wang, Lei Huang
Federated Learning Federated Prompt Cooperation Client Selection DIstribution Estimation Client Heterogeneity Device Selection

May 7, 2024

Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning
Chunlin Tian, Zhan Shi, Xinpeng Qin, Li Li, Chengzhong Xu
Federated Learning Imitation Learning Client Selection Pairwise Learning Training Convergence Device Selection

April 20, 2024

A SER-based Device Selection Mechanism in Multi-bits Quantization Federated Learning
Pengcheng Sun, Erwu Liu, Rui Wang
Non Orthogonal Multiple Access Interference Cancellation Wireless Channel Device Selection Error Bit

November 22, 2023

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems
Chentao Jia, Ming Hu, Zekai Chen, Yanxin Yang, Xiaofei Xie, Yang Liu, Mingsong Chen
Fine Grained Heterogeneous Federated Learning Artificial Intelligence of Thing Device Selection

August 1, 2023

AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy
Zihao Zhao, Yuzhu Mao, Zhenpeng Shi, Yang Liu, Tian Lan, Wenbo Ding, Xiao-Ping Zhang
Quantization Technique Quantization Level Adaptive Quantization Communication Efficient Federated Learning Device Selection

December 22, 2022

Device Selection for the Coexistence of URLLC and Distributed Learning Services
Milad Ganjalizadeh, Hossein Shokri Ghadikolaei, Deniz Gündüz, Marina Petrova
Artificial Intelligence AI Service Artificial Intelligence Training Ultra Reliable Low Latency Communication Device Selection Human Autonomy Coexistence

March 10, 2022

A Contribution-based Device Selection Scheme in Federated Learning
Shashi Raj Pandey, Lam D. Nguyen, Petar Popovski
Strong Generalization Device Variation Device Selection

November 19, 2021

Client Selection in Federated Learning based on Gradients Importance
Ouiame Marnissi, Hajar El Hammouti, El Houcine Bergou
Heterogeneous Data Gradient Norm Client Selection Communication Efficiency Gradient Information Device Selection

Device Selection

Papers

Resource Efficient Asynchronous Federated Learning for Digital Twin Empowered IoT Network

Efficient Data Distribution Estimation for Accelerated Federated Learning

Ranking-based Client Selection with Imitation Learning for Efficient Federated Learning

A SER-based Device Selection Mechanism in Multi-bits Quantization Federated Learning

AdaptiveFL: Adaptive Heterogeneous Federated Learning for Resource-Constrained AIoT Systems

AQUILA: Communication Efficient Federated Learning with Adaptive Quantization in Device Selection Strategy

Device Selection for the Coexistence of URLLC and Distributed Learning Services

A Contribution-based Device Selection Scheme in Federated Learning

Client Selection in Federated Learning based on Gradients Importance