Federated Edge Learning

Federated Edge Learning (FEEL) is a distributed machine learning paradigm enabling collaborative model training across numerous edge devices without directly sharing their private data. Current research emphasizes addressing challenges like data heterogeneity (non-IID data) through techniques such as dataset distillation, adaptive quantization, and clustered data sharing, often employing variations of FedAvg and incorporating over-the-air computation for efficient model aggregation. This approach is significant for its potential to improve the efficiency and scalability of machine learning in resource-constrained environments while preserving data privacy, with applications ranging from autonomous driving and IoT to satellite networks and healthcare.

Papers

October 14, 2024

Mobility-Aware Federated Learning: Multi-Armed Bandit Based Selection in Vehicular Network
Haoyu Tu, Lin Chen, Zuguang Li, Xiaopei Chen, Wen Wu
Multi Armed Bandit View Selection Vehicular Network Federated Edge Learning

October 10, 2024

A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning
Jingbo Zhang, Qiong Wu, Pingyi Fan, Qiang Fan
Comprehensive Survey Resource Allocation Joint Optimization Federated Edge Learning Resource Optimization

September 26, 2024

Dataset Distillation-based Hybrid Federated Learning on Non-IID Data
Xiufang Shi, Wei Zhang, Mincheng Wu, Guangyi Liu, Zhenyu Wen, Shibo He, Tejal Shah, Rajiv Ranjan
Data Set Raw Data Label Distribution Federated Edge Learning Unobserved Heterogeneity Distilled Dataset Heterogeneous Cluster

September 17, 2024

FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction
Ziwei Li, Xiaoqi Wang, Hong-You Chen, Han-Wei Shen, Wei-Lun Chao
Graph Learning Dimensionality Reduction Model Training Federated Edge Learning Stochastic Neighbor Embedding

August 10, 2024

FedRobo: Federated Learning Driven Autonomous Inter Robots Communication For Optimal Chemical Sprays
Jannatul Ferdaus, Sameera Pisupati, Mahedi Hasan, Sathwick Paladugu
Autonomous Robot Federated Edge Learning Chemical Spray

July 16, 2024

Scalable and Reliable Over-the-Air Federated Edge Learning
Maximilian Egger, Christoph Hofmeister, Cem Kaya, Rawad Bitar, Antonia Wachter-Zeh
Potential Scalability Federated Edge Learning Air Federated Learning Air Computation Multiple Access

July 3, 2024

Joint Optimization of Resource Allocation and Data Selection for Fast and Cost-Efficient Federated Edge Learning
Yunjian Jia, Zhen Huang, Jiping Yan, Yulu Zhang, Kun Luo, Wanli Wen
Resource Allocation Data Selection Joint Optimization Federated Edge Learning Edge Learning Convex Concave Wireless Edge Gradient Projection

June 26, 2024

FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization
Linping Qu, Shenghui Song, Chi-Ying Tsui
Wireless Network Federated Edge Learning Uplink Control Downlink Adaptive Quantization

June 25, 2024

Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learning
Jintao Yan, Tan Chen, Yuxuan Sun, Zhaojun Nan, Sheng Zhou, Zhisheng Niu
Vehicular Network Federated Edge Learning Dynamic Scheduling Connected Vehicle Vehicle 2 Vehicle Vehicle to Vehicle

June 14, 2024

Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Clustered Data Sharing Approach
Gang Hu, Yinglei Teng, Nan Wang, Zhu Han
Adaptive Importance Faster Convergence Data Sharing Federated Edge Learning Collective Communication

May 22, 2024

FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillation
Quyang Pan, Sheng Sun, Zhiyuan Wu, Yuwei Wang, Min Liu, Bo Gao, Jingyuan Wang
Federated Learning Full Potential Federated Edge Learning Distilled Dataset Knowledge Storage

May 20, 2024

Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach
Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson
Resource Allocation Lyapunov Function Federated Edge Learning Stochastic Optimization Problem Edge Learning Streaming Data

May 9, 2024

Privacy-Preserving Edge Federated Learning for Intelligent Mobile-Health Systems
Amin Aminifar, Matin Shokri, Amir Aminifar
Machine Learning Federated Edge Learning Privacy Preserving Federated Learning Intelligent Healthcare Wearable Technology

May 2, 2024

Causal Influence in Federated Edge Inference
Mert Kayaalp, Yunus Inan, Visa Koivunen, Ali H. Sayed
Scientific Inference Agent Behavior Heterogeneous Agent Federated Edge Learning Causal Influence Local Inference

April 2, 2024

Satellite Federated Edge Learning: Architecture Design and Convergence Analysis
Yuanming Shi, Li Zeng, Jingyang Zhu, Yong Zhou, Chunxiao Jiang, Khaled B. Letaief
Convergence Analysis Architecture Design Federated Edge Learning Satellite Constellation Orbit Model Low Earth Orbit Satellite

January 28, 2024

Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learning
Mohamed Elmahallawy, Tie Luo
Extreme Edge Federated Edge Learning Model Retraining Low Earth Orbit Wireless Edge Energy Efficient Training

January 13, 2024

FedDriveScore: Federated Scoring Driving Behavior with a Mixture of Metric Distributions
Lin Lu
Mixture Component Federated Edge Learning Centralized Learning Metric Distribution Vehicle Road Cloud

January 1, 2024

Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDM
Mohamed Elmahallawy, Tie Luo, Khaled Ramadan
Federated Edge Learning Non Orthogonal Multiple Access Low Earth Orbit Satellite Communication Satellite Terrestrial High Altitude Platform

November 30, 2023

Federated Edge Learning

Papers

Mobility-Aware Federated Learning: Multi-Armed Bandit Based Selection in Vehicular Network

A Comprehensive Survey on Joint Resource Allocation Strategies in Federated Edge Learning

Dataset Distillation-based Hybrid Federated Learning on Non-IID Data

FedNE: Surrogate-Assisted Federated Neighbor Embedding for Dimensionality Reduction

FedRobo: Federated Learning Driven Autonomous Inter Robots Communication For Optimal Chemical Sprays

Scalable and Reliable Over-the-Air Federated Edge Learning

Joint Optimization of Resource Allocation and Data Selection for Fast and Cost-Efficient Federated Edge Learning

FedAQ: Communication-Efficient Federated Edge Learning via Joint Uplink and Downlink Adaptive Quantization

Dynamic Scheduling for Vehicle-to-Vehicle Communications Enhanced Federated Learning

Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Clustered Data Sharing Approach

FedCache 2.0: Federated Edge Learning with Knowledge Caching and Dataset Distillation

Energy-Efficient Federated Edge Learning with Streaming Data: A Lyapunov Optimization Approach

Privacy-Preserving Edge Federated Learning for Intelligent Mobile-Health Systems

Causal Influence in Federated Edge Inference

Satellite Federated Edge Learning: Architecture Design and Convergence Analysis

Stitching Satellites to the Edge: Pervasive and Efficient Federated LEO Satellite Learning

FedDriveScore: Federated Scoring Driving Behavior with a Mixture of Metric Distributions

Communication-Efficient Federated Learning for LEO Satellite Networks Integrated with HAPs Using Hybrid NOMA-OFDM

VREM-FL: Mobility-Aware Computation-Scheduling Co-Design for Vehicular Federated Learning

FedEmb: A Vertical and Hybrid Federated Learning Algorithm using Network And Feature Embedding Aggregation