# Balancing Energy Efficiency and Distributional Robustness in Over-the-Air Federated Learning

arXiv: https://arxiv.org/abs/2312.14638 · HTML: https://mlsanity.com/paper/2312.14638/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 12 references that are in the map.
- First posted on arXiv 22 Dec 2023.

## Builds on (most cited first, 7 of 7)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Agnostic Federated Learning](https://mlsanity.com/paper/1902.00146/) (2019)
- [Distributionally Robust Federated Averaging](https://mlsanity.com/paper/2102.12660/) (2021)
- [Harnessing Wireless Channels for Scalable and Privacy-Preserving Federated Learning](https://mlsanity.com/paper/2007.01790/) (2020)
- [Gradient and Channel Aware Dynamic Scheduling for Over-the-Air Computation in Federated Edge Learning Systems](https://mlsanity.com/paper/2212.00491/) (2022)
- [Communication-Efficient Distributionally Robust Decentralized Learning](https://mlsanity.com/paper/2205.15614/) (2022)
- [DR-DSGD: A Distributionally Robust Decentralized Learning Algorithm over Graphs](https://mlsanity.com/paper/2208.13810/) (2022)

## Built on by (most cited first, 1 of 1)

- [Distributionally Robust Federated Learning with Client Drift Minimization](https://mlsanity.com/paper/2505.15371/) (2025)

## Abstract (arXiv)

The growing number of wireless edge devices has magnified challenges concerning energy, bandwidth, latency, and data heterogeneity. These challenges have become bottlenecks for distributed learning. To address these issues, this paper presents a novel approach that ensures energy efficiency for distributionally robust federated learning (FL) with over air computation (AirComp). In this context, to effectively balance robustness with energy efficiency, we introduce a novel client selection method that integrates two complementary insights: a deterministic one that is designed for energy efficiency, and a probabilistic one designed for distributional robustness. Simulation results underscore the efficacy of the proposed algorithm, revealing its superior performance compared to baselines from both robustness and energy efficiency perspectives, achieving more than 3-fold energy savings compared to the considered baselines.