# Hierarchical Over-the-Air Federated Edge Learning

arXiv: https://arxiv.org/abs/2112.11167 · HTML: https://mlsanity.com/paper/2112.11167/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 23 references that are in the map.
- First posted on arXiv 21 Dec 2021.

## Builds on (most cited first, 15 of 15)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Federated Learning in Mobile Edge Networks: A Comprehensive Survey](https://mlsanity.com/paper/1909.11875/) (2019)
- [Federated learning with hierarchical clustering of local updates to improve training on non-IID data](https://mlsanity.com/paper/2004.11791/) (2020)
- [Client-Edge-Cloud Hierarchical Federated Learning](https://mlsanity.com/paper/1905.06641/) (2019)
- [Broadband Analog Aggregation for Low-Latency Federated Edge Learning (Extended Version)](https://mlsanity.com/paper/1812.11494/) (2018)
- [One-Bit Over-the-Air Aggregation for Communication-Efficient Federated Edge Learning: Design and Convergence Analysis](https://mlsanity.com/paper/2001.05713/) (2020)
- [Hierarchical Federated Learning Across Heterogeneous Cellular Networks](https://mlsanity.com/paper/1909.02362/) (2019)
- [Federated Learning over Wireless Networks: Convergence Analysis and Resource Allocation](https://mlsanity.com/paper/1910.13067/) (2019)
- [HFEL: Joint Edge Association and Resource Allocation for Cost-Efficient Hierarchical Federated Edge Learning](https://mlsanity.com/paper/2002.11343/) (2020)
- [Over-the-Air Federated Learning from Heterogeneous Data](https://mlsanity.com/paper/2009.12787/) (2020)
- [Privacy For Free: Wireless Federated Learning Via Uncoded Transmission With Adaptive Power Control](https://mlsanity.com/paper/2006.05459/) (2020)
- [Blind Federated Edge Learning](https://mlsanity.com/paper/2010.10030/) (2020)
- [Convergence of Federated Learning over a Noisy Downlink](https://mlsanity.com/paper/2008.11141/) (2020)
- [Federated Learning with Downlink Device Selection](https://mlsanity.com/paper/2107.03510/) (2021)

## Built on by (most cited first, 11 of 11)

- [A Survey on Over-the-Air Computation](https://mlsanity.com/paper/2210.11350/) (2022)
- [Scalable Hierarchical Over-the-Air Federated Learning](https://mlsanity.com/paper/2211.16162/) (2022)
- [Training Machine Learning models at the Edge: A Survey](https://mlsanity.com/paper/2403.02619/) (2024)
- [Over-the-Air Federated Edge Learning with Hierarchical Clustering](https://mlsanity.com/paper/2207.09232/) (2022)
- [Advancements in Federated Learning: Models, Methods, and Privacy](https://mlsanity.com/paper/2302.11466/) (2023)
- [Hierarchical Over-the-Air Federated Learning with Awareness of Interference and Data Heterogeneity](https://mlsanity.com/paper/2401.01442/) (2024)
- [Communication-Efficient and Privacy-Preserving Feature-based Federated Transfer Learning](https://mlsanity.com/paper/2209.05395/) (2022)
- [Graph Neural Networks over the Air for Decentralized Tasks in Wireless Networks](https://mlsanity.com/paper/2302.08447/) (2023)
- [Hierarchical Over-the-Air FedGradNorm](https://mlsanity.com/paper/2212.07414/) (2022)
- [Feature-based Federated Transfer Learning: Communication Efficiency, Robustness and Privacy](https://mlsanity.com/paper/2405.09014/) (2024)
- [A Hierarchical Federated Learning Approach for the Internet of Things](https://mlsanity.com/paper/2403.01540/) (2024)

## Abstract (arXiv)

Federated learning (FL) over wireless communication channels, specifically, over-the-air (OTA) model aggregation framework is considered. In OTA wireless setups, the adverse channel effects can be alleviated by increasing the number of receive antennas at the parameter server (PS), which performs model aggregation. However, the performance of OTA FL is limited by the presence of mobile users (MUs) located far away from the PS. In this paper, to mitigate this limitation, we propose hierarchical over-the-air federated learning (HOTAFL), which utilizes intermediary servers (IS) to form clusters near MUs. We provide a convergence analysis for the proposed setup, and demonstrate through theoretical and experimental results that local aggregation in each cluster before global aggregation leads to a better performance and faster convergence than OTA FL.