Air Federated Learning

Air Federated Learning (AirFL) aims to improve the efficiency of federated learning by leveraging the superposition property of wireless channels to aggregate model updates from multiple devices simultaneously, reducing communication overhead and latency. Current research focuses on optimizing various aspects of AirFL, including client selection strategies, weighted aggregation techniques, and the use of advanced coding and modulation schemes to mitigate the effects of channel noise and heterogeneity. This approach holds significant promise for enabling large-scale distributed machine learning in resource-constrained environments, particularly in applications like the Internet of Things and edge computing, by improving both privacy and efficiency.

Papers

June 3, 2023

Over-the-Air Federated Learning In Broadband Communication
Wayne Lemieux, Raphael Pinard, Mitra Hassani
Differential Privacy Multiple Input Multiple Output Inference Attack Air Federated Learning Secure Multiparty Computation

May 26, 2023

Channel and Gradient-Importance Aware Device Scheduling for Over-the-Air Federated Learning
Yuchang Sun, Zehong lin, Yuyi Mao, Shi Jin, Jun Zhang
Air Federated Learning Air Computation Channel Quality Uplink Control Device Scheduling

May 10, 2023

Spectrum Breathing: Protecting Over-the-Air Federated Learning Against Interference
Zhanwei Wang, Kaibin Huang, Yonina C. Eldar
Catastrophic Interference Air Federated Learning Multi Cell Interference Mitigation

May 5, 2023

Over-the-Air Federated Averaging with Limited Power and Privacy Budgets
Na Yan, Kezhi Wang, Cunhua Pan, Kok Keong Chai, Feng Shu, Jiangzhou Wang
Differential Privacy Air Federated Learning Privacy Budget Privacy Constraint Novel Over the Air Second

February 4, 2023

Digital Over-the-Air Federated Learning in Multi-Antenna Systems
Sihua Wang, Mingzhe Chen, Cong Shen, Changchuan Yin, Christopher G. Brinton
Multiple Input Multiple Output Air Federated Learning Beamforming Design

January 24, 2023

PolarAir: A Compressed Sensing Scheme for Over-the-Air Federated Learning
Michail Gkagkos, Krishna R. Narayanan, Jean-Francois Chamberland, Costas N. Georghiades
Linear Compression Compressed Sensing Air Federated Learning Gaussian Channel Compression Scheme

December 13, 2022

Over-The-Air Federated Learning Over Scalable Cell-free Massive MIMO
Houssem Sifaou, Geoffrey Ye Li
Air Federated Learning Air Computation Multiple Access Channel Correlation

November 25, 2022

Inverse Feasibility in Over-the-Air Federated Learning
Tomasz Piotrowski, Rafail Ismayilov, Matthias Frey, Renato L. G. Cavalcante
Ill Posed Inverse Problem Air Federated Learning Forward Model Learning Feasibility

November 7, 2022

Over-The-Air Clustered Wireless Federated Learning
Ayush Madhan-Sohini, Divin Dominic, Nazreen Shah, Ranjitha Prasad
Decentralized Federated Learning Air Federated Learning Consensus 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 5, 2022

Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations
Jialing Liao, Zheng Chen, Erik G. Larsson
Differential Privacy PRIvacy Leakage Additive Perturbation Air Federated Learning Waveform Domain Multiple Access

July 19, 2022

Over-the-Air Federated Edge Learning with Hierarchical Clustering
Ozan Aygün, Mohammad Kazemi, Deniz Gündüz, Tolga M. Duman
Federated Learning Hierarchical Clustering Faster Convergence Air Federated Learning Global Aggregation Air Aggregation Two Stage Aggregation

July 17, 2022

Balancing Accuracy and Integrity for Reconfigurable Intelligent Surface-aided Over-the-Air Federated Learning
Jingheng Zheng, Hui Tian, Wanli Ni, Wei Ni, Ping Zhang
Channel State Information Adaptive Beamforming Channel Estimation Air Federated Learning Air Computation Reconfigurable Intelligent

June 14, 2022

Matching Pursuit Based Scheduling for Over-the-Air Federated Learning
Ali Bereyhi, Adela Vagollari, Saba Asaad, Ralf R. Müller, Wolfgang Gerstacker, H. Vincent Poor
Convex Relaxation Air Federated Learning Near Optimal Known Algorithm Aware Job Device Scheduling

June 6, 2022

Interference Management for Over-the-Air Federated Learning in Multi-Cell Wireless Networks
Zhibin Wang, Yong Zhou, Yuanming Shi, Weihua Zhuang
Federated Learning Air Federated Learning Uplink Control Multi Cell Gradient Aggregation Interference Management

May 12, 2022

Over-the-Air Federated Learning with Joint Adaptive Computation and Power Control
Haibo Yang, Peiwen Qiu, Jia Liu, Aylin Yener
Air Federated Learning Power Control Joint Distribution Adaptation Noisy Communication

May 8, 2022

Over-the-Air Federated Multi-Task Learning via Model Sparsification and Turbo Compressed Sensing
Haoming Ma, Xiaojun Yuan, Zhi Ding, Dian Fan, Jun Fang
Compressed Sensing Communication Efficient Air Federated Learning Air Computation Model Sparsification Orthogonal Multiple Access Power Constraint

May 5, 2022

Over-The-Air Federated Learning under Byzantine Attacks
Houssem Sifaou, Geoffrey Ye Li
Air Federated Learning Air Computation Byzantine Attack Robust Aggregation

March 31, 2022

Differentially Private Federated Learning via Reconfigurable Intelligent Surface
Yuhan Yang, Yong Zhou, Youlong Wu, Yuanming Shi
Private Federated Learning Air Federated Learning Air Computation Reconfigurable Intelligent Surface Radio Environment

March 29, 2022

Over-the-Air Federated Learning via Second-Order Optimization
Peng Yang, Yuning Jiang, Ting Wang, Yong Zhou, Yuanming Shi, Colin N. Jones
Air Federated Learning Federated Optimization Local Convergence Multiple Access Second Order Optimization Novel Over the Air Second