Air Aggregation

Air aggregation, also known as over-the-air computation, is a technique leveraging the superposition property of wireless channels to aggregate data from multiple devices simultaneously, significantly reducing communication overhead in distributed machine learning and inference tasks. Current research focuses on optimizing this aggregation for federated learning, exploring various model architectures and algorithms to improve accuracy and privacy while addressing challenges like heterogeneous device capabilities, channel noise, and data imbalances. This approach holds significant promise for improving the efficiency and scalability of large-scale distributed applications, particularly in resource-constrained edge computing environments.

Papers

October 10, 2024

Scalable and Resource-Efficient Second-Order Federated Learning via Over-the-Air Aggregation
Abdulmomen Ghalkha, Chaouki Ben Issaid, Mehdi Bennis
Federated Learning Hessian Matrix Faster Convergence Air Aggregation Network Bottleneck

July 30, 2024

Private Collaborative Edge Inference via Over-the-Air Computation
Selim F. Yilmaz, Burak Hasircioglu, Li Qiao, Deniz Gunduz
Exact Inference Air Computation Collaborative Inference Air Aggregation Private Bayesian

June 4, 2024

Mixed-Precision Federated Learning via Multi-Precision Over-The-Air Aggregation
Jinsheng Yuan, Zhuangkun Wei, Weisi Guo
Air Federated Learning Approximate Computing Air Aggregation

May 31, 2024

Waveform Design for Over-the-Air Computing
Nikos G. Evgenidis, Nikos A. Mitsiou, Sotiris A. Tegos, Panagiotis D. Diamantoulakis, Panagiotis Sarigiannidis, Ioannis T. Rekanos, George K. Karagiannidis
Concurrent Transmission Air Aggregation Novel Over the Air Second Transceiver Design Waveform Design

December 15, 2023

Device Scheduling for Relay-assisted Over-the-Air Aggregation in Federated Learning
Fan Zhang, Jining Chen, Kunlun Wang, Wen Chen
Federated Learning Power Allocation Air Aggregation Device Scheduling

October 25, 2023

Over-the-air Federated Policy Gradient
Huiwen Yang, Lingying Huang, Subhrakanti Dey, Ling Shi
Optimization Purpose Distortion Aware Air Federated Learning Policy Gradient Algorithm Novel Over the Air Second Air Aggregation

July 3, 2023

Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions
Bingnan Xiao, Xichen Yu, Wei Ni, Xin Wang, H. Vincent Poor
Future Direction Open Challenge Edge Network Air Federated Learning Chaotic Regime Multiple Access Air Aggregation

June 4, 2023

Riemannian Low-Rank Model Compression for Federated Learning with Over-the-Air Aggregation
Ye Xue, Vincent Lau
Model Compression Low Rank Low Dimensional Manifold Riemannian Geometry Approach Low Rank Compression Low Rank Constraint Air Aggregation

November 29, 2022

Scalable Hierarchical Over-the-Air Federated Learning
Seyed Mohammad Azimi-Abarghouyi, Viktoria Fodor
Potential Scalability Air Aggregation Downlink Communication Gradient Aggregation

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

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

February 7, 2022

Over-the-Air Ensemble Inference with Model Privacy
Selim F. Yilmaz, Burak Hasircioglu, Deniz Gunduz
Scientific Inference Exact Inference Model Privacy Wireless Edge Air Aggregation