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 25, 2023

Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channels
Zheshun Wu, Zenglin Xu, Hongfang Yu, Jie Liu
Edge Intelligence Federated Edge Learning Noisy Channel Information Theoretic Generalization

July 21, 2023

Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning
Yao Wen, Guopeng Zhang, Kezhi Wang, Kun Yang
Deep Neural Network Edge Computing Federated Edge Learning Cut Selection Latency Training

June 17, 2023

Edge Intelligence Over the Air: Two Faces of Interference in Federated Learning
Zihan Chen, Howard H. Yang, Tony Q. S. Quek
Human Face Catastrophic Interference Edge Intelligence Federated Edge Learning Air Computation Next Generation Wireless Network

June 5, 2023

Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning
Yao Tang, Guangxu Zhu, Wei Xu, Man Hon Cheung, Tat-Ming Lok, Shuguang Cui
Timely Communication Computation Method Federated Edge Learning Integrated Sensing

May 2, 2023

Dynamic Scheduling for Federated Edge Learning with Streaming Data
Chung-Hsuan Hu, Zheng Chen, Erik G. Larsson
Federated Edge Learning Stochastic Optimization Problem Dynamic Scheduling Streaming Data Dynamic Importance

March 21, 2023

Poisoning Attacks in Federated Edge Learning for Digital Twin 6G-enabled IoTs: An Anticipatory Study
Mohamed Amine Ferrag, Burak Kantarci, Lucas C. Cordeiro, Merouane Debbah, Kim-Kwang Raymond Choo
Federated Learning Digital Twin Internet of Thing Poisoning Attack Internet of Thing Device IOT Technology Federated Edge Learning Internet of Thing Environment Episodic Future Thinking

March 11, 2023

Reducing Non-IID Effects in Federated Autonomous Driving with Contrastive Divergence Loss
Tuong Do, Binh X. Nguyen, Hien Nguyen, Erman Tjiputra, Quang D. Tran, Te-Chuan Chiu, Anh Nguyen
Autonomous Driving Mixed Effect Federated Edge Learning Contrastive Divergence Divergence Loss

February 24, 2023

Personalizing Federated Learning with Over-the-Air Computations
Zihan Chen, Zeshen Li, Howard H. Yang, Tony Q. S. Quek
Federated Edge Learning Air Computation Edge Server Training Paradigm

January 14, 2023

Knowledge Distillation in Federated Edge Learning: A Survey
Zhiyuan Wu, Sheng Sun, Yuwei Wang, Min Liu, Xuefeng Jiang, Runhan Li, Bo Gao
Timely Survey Knowledge Distillation Internet of Thing Federated Edge Learning Federated Distillation Device Machine Learning

October 31, 2022

Blind Asynchronous Over-the-Air Federated Edge Learning
Saeed Razavikia, Jaume Anguera Peris, Jose Mairton B. da Silva, Carlo Fischione
Convex Optimization Federated Edge Learning Air Federated Learning Air Computation

October 27, 2022

Resource Constrained Vehicular Edge Federated Learning with Highly Mobile Connected Vehicles
Md Ferdous Pervej, Richeng Jin, Huaiyu Dai
Federated Edge Learning Edge Server Connected Vehicle Vehicle to Infrastructure

October 14, 2022

A Primal-Dual Algorithm for Hybrid Federated Learning
Tom Overman, Garrett Blum, Diego Klabjan
LeArning Abstract Federated Edge Learning Robust Algorithm Primal Dual Algorithm Strong Duality FL Algorithm

October 13, 2022

Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learning
Alphan Sahin
Channel Estimation Federated Edge Learning Air Computation Edge Learning Orthogonal Frequency Division Multiplexing Numeral System Non Coherent Receiver

September 20, 2022

A Demonstration of Over-the-Air Computation for Federated Edge Learning
Alphan Sahin
Textual Demonstration Federated Edge Learning Air Computation Software Defined Radio Frequency Modulation

June 22, 2022

FedorAS: Federated Architecture Search under system heterogeneity
Lukasz Dudziak, Stefanos Laskaridis, Javier Fernandez-Marques
Neural Architecture Search Federated Edge Learning Heterogeneous Environment System Heterogeneity

June 3, 2022

Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification
Shuai Wang, Chengyang Li, Derrick Wing Kwan Ng, Yonina C. Eldar, H. Vincent Poor, Qi Hao, Chengzhong Xu
Autonomous Vehicle Product Design Verification Task Vehicular Network Federated Edge Learning Sensor Placement Autonomous Vehicle Perception Federated Deep Interactive Driving

April 1, 2022

Accelerating Federated Edge Learning via Topology Optimization
Shanfeng Huang, Zezhong Zhang, Shuai Wang, Rui Wang, Kaibin Huang
Topology Optimization Federated Edge Learning Deep Imitation

February 23, 2022

Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search
Chunhui Zhang, Xiaoming Yuan, Qianyun Zhang, Guangxu Zhu, Lei Cheng, Ning Zhang
Neural Architecture Search Federated Edge Learning Artificial Intelligence of Thing Device Heterogeneity

February 17, 2022

Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning
Yuxuan Sun, Sheng Zhou, Zhisheng Niu, Deniz Gündüz
Federated Learning Model Aggregation Federated Edge Learning Unstructured Sparsity Top K Sparsification Air Aggregation

January 8, 2022

A Fair and Efficient Hybrid Federated Learning Framework based on XGBoost for Distributed Power Prediction
Haizhou Liu, Xuan Zhang, Xinwei Shen, Hongbin Sun
Real Time Vertical Federated Learning XGBoost Model Federated Edge Learning Computational Power Power Prediction

Federated Edge Learning

Papers

Information-Theoretic Generalization Analysis for Topology-aware Heterogeneous Federated Edge Learning over Noisy Channels

Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning

Edge Intelligence Over the Air: Two Faces of Interference in Federated Learning

Integrated Sensing, Computation, and Communication for UAV-assisted Federated Edge Learning

Dynamic Scheduling for Federated Edge Learning with Streaming Data

Poisoning Attacks in Federated Edge Learning for Digital Twin 6G-enabled IoTs: An Anticipatory Study

Reducing Non-IID Effects in Federated Autonomous Driving with Contrastive Divergence Loss

Personalizing Federated Learning with Over-the-Air Computations

Knowledge Distillation in Federated Edge Learning: A Survey

Blind Asynchronous Over-the-Air Federated Edge Learning

Resource Constrained Vehicular Edge Federated Learning with Highly Mobile Connected Vehicles

A Primal-Dual Algorithm for Hybrid Federated Learning

Over-the-Air Computation Based on Balanced Number Systems for Federated Edge Learning

A Demonstration of Over-the-Air Computation for Federated Edge Learning

FedorAS: Federated Architecture Search under system heterogeneity

Federated Deep Learning Meets Autonomous Vehicle Perception: Design and Verification

Accelerating Federated Edge Learning via Topology Optimization

Towards Tailored Models on Private AIoT Devices: Federated Direct Neural Architecture Search

Time-Correlated Sparsification for Efficient Over-the-Air Model Aggregation in Wireless Federated Learning

A Fair and Efficient Hybrid Federated Learning Framework based on XGBoost for Distributed Power Prediction