Heterogeneous Wireless

Heterogeneous wireless networks pose significant challenges for federated learning (FL), where diverse devices with varying computational capabilities and wireless conditions collaboratively train machine learning models. Current research focuses on optimizing FL efficiency in these heterogeneous environments by developing novel participant selection strategies, adjusting learning rates based on device capabilities and channel conditions, and employing over-the-air computation to reduce communication overhead. These advancements aim to improve the accuracy and speed of FL while mitigating issues like model staleness and energy consumption, impacting applications ranging from mobile health to smart city infrastructure.

Papers

July 1, 2024

FedEx: Expediting Federated Learning over Heterogeneous Mobile Devices by Overlapping and Participant Selection
Jiaxiang Geng, Boyu Li, Xiaoqi Qin, Yixuan Li, Liang Li, Yanzhao Hou, Miao Pan
Federated Learning Heterogeneous Device Heterogeneous Wireless Gradient Communication Participant Selection Latency Training

April 23, 2024

FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks
Bingnan Xiao, Jingjing Zhang, Wei Ni, Xin Wang
Federated Learning Learning Rate Wireless Network Scheduling Policy Heterogeneous Wireless Training Iteration

March 28, 2024

Biased Over-the-Air Federated Learning under Wireless Heterogeneity
Muhammad Faraz Ul Abrar, Nicolò Michelusi
Air Federated Learning Heterogeneous Wireless

September 25, 2023

Estimating Treatment Effects Under Heterogeneous Interference
Xiaofeng Lin, Guoxi Zhang, Xiaotian Lu, Han Bao, Koh Takeuchi, Hisashi Kashima
Estimation Task Treatment Effect Individual Treatment Effect Treatment Effect Estimation Network Interference Heterogeneous Wireless

September 24, 2023

REWAFL: Residual Energy and Wireless Aware Participant Selection for Efficient Federated Learning over Mobile Devices
Y. Li, X. Qin, J. Geng, R. Chen, Y. Hou, Y. Gong, M. Pan, P. Zhang
Federated Learning Mobile Device Heterogeneous Wireless Residual Physic Federated Learning Training

August 24, 2023

Perimeter Control with Heterogeneous Metering Rates for Cordon Signals: A Physics-Regularized Multi-Agent Reinforcement Learning Approach
Jiajie Yu, Pierre-Antoine Laharotte, Yu Han, Wei Ma, Ludovic Leclercq
Reinforcement Learning Multi Agent Reinforcement Learning Traffic Signal Control Heterogeneous Wireless Perimeter Defense Signal Control

August 17, 2023

Joint Power Control and Data Size Selection for Over-the-Air Computation Aided Federated Learning
Xuming An, Rongfei Fan, Shiyuan Zuo, Han Hu, Hai Jiang, Ning Zhang
Air Federated Learning Air Computation Dataset Size Heterogeneous Wireless Spectrum Utilization Signal Map Joint Power

May 29, 2023

Bandwidth Optimal Pipeline Schedule for Collective Communication
Liangyu Zhao, Arvind Krishnamurthy
Polynomial Time Efficient Pipeline Network Topology Dynamic Bandwidth Heterogeneous Wireless Collective Communication

October 25, 2022

Learning Individual Treatment Effects under Heterogeneous Interference in Networks
Ziyu Zhao, Yuqi Bai, Kun Kuang, Ruoxuan Xiong, Fei Wu
Network Programming Individual Treatment Effect Spillover Effect Treatment Effect Estimation Heterogeneous Wireless Valued Treatment

May 13, 2022

Multi-variant COVID-19 model with heterogeneous transmission rates using deep neural networks
K. D. Olumoyin, A. Q. M. Khaliq, K. M. Furati
Deep Neural Network Sars Cov 2 Variant Pathogenicity Heterogeneous Wireless SARS CoV 2 Variant Susceptible Infected

April 21, 2022

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump
Sihao Hu, Zhen Zhang, Shengliang Lu, Bingsheng He, Zhao Li
Heterogeneous Wireless Target Prediction

April 7, 2022

Few-Shot Forecasting of Time-Series with Heterogeneous Channels
Lukas Brinkmeyer, Rafael Rego Drumond, Johannes Burchert, Lars Schmidt-Thieme
Time Series Time Series Forecasting Multivariate Time Series State of the Art Forecasting Shot Classification Heterogeneous Wireless Shot Forecasting

February 26, 2022

Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression
Anu Jagannath, Jithin Jagannath
Multi Task Learning Model Compression Digital Modulation Signal Classification Edge Deployment Heterogeneous Wireless Spectral Angle Awareness

February 21, 2022

The Role of Heterogeneity in Autonomous Perimeter Defense Problems
Aviv Adler, Oscar Mickelin, Ragesh K. Ramachandran, Gaurav S. Sukhatme, Sertac Karaman
Integral Role Dynamic Programming Heterogeneous Team Heterogeneous Wireless Perimeter Defense Autonomous Multi Robot Team

December 27, 2021

Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channels
Chenxi Zhong, Huiyuan Yang, Xiaojun Yuan
Multiple Input Multiple Output Adaptive Beamforming Air Federated Learning Air Computation Heterogeneous Wireless

Heterogeneous Wireless

Papers

FedEx: Expediting Federated Learning over Heterogeneous Mobile Devices by Overlapping and Participant Selection

FLARE: A New Federated Learning Framework with Adjustable Learning Rates over Resource-Constrained Wireless Networks

Biased Over-the-Air Federated Learning under Wireless Heterogeneity

Estimating Treatment Effects Under Heterogeneous Interference

REWAFL: Residual Energy and Wireless Aware Participant Selection for Efficient Federated Learning over Mobile Devices

Perimeter Control with Heterogeneous Metering Rates for Cordon Signals: A Physics-Regularized Multi-Agent Reinforcement Learning Approach

Joint Power Control and Data Size Selection for Over-the-Air Computation Aided Federated Learning

Bandwidth Optimal Pipeline Schedule for Collective Communication

Learning Individual Treatment Effects under Heterogeneous Interference in Networks

Multi-variant COVID-19 model with heterogeneous transmission rates using deep neural networks

Sequence-Based Target Coin Prediction for Cryptocurrency Pump-and-Dump

Few-Shot Forecasting of Time-Series with Heterogeneous Channels

Multi-task Learning Approach for Modulation and Wireless Signal Classification for 5G and Beyond: Edge Deployment via Model Compression

The Role of Heterogeneity in Autonomous Perimeter Defense Problems

Over-the-Air Federated Multi-Task Learning Over MIMO Multiple Access Channels