تقرير
Biased Over-the-Air Federated Learning under Wireless Heterogeneity
العنوان: | Biased Over-the-Air Federated Learning under Wireless Heterogeneity |
---|---|
المؤلفون: | Abrar, Muhammad Faraz Ul, Michelusi, Nicolò |
سنة النشر: | 2024 |
المجموعة: | Computer Science |
مصطلحات موضوعية: | Computer Science - Machine Learning, Electrical Engineering and Systems Science - Signal Processing |
الوصف: | Recently, Over-the-Air (OTA) computation has emerged as a promising federated learning (FL) paradigm that leverages the waveform superposition properties of the wireless channel to realize fast model updates. Prior work focused on the OTA device ``pre-scaler" design under \emph{homogeneous} wireless conditions, in which devices experience the same average path loss, resulting in zero-bias solutions. Yet, zero-bias designs are limited by the device with the worst average path loss and hence may perform poorly in \emph{heterogeneous} wireless settings. In this scenario, there may be a benefit in designing \emph{biased} solutions, in exchange for a lower variance in the model updates. To optimize this trade-off, we study the design of OTA device pre-scalers by focusing on the OTA-FL convergence. We derive an upper bound on the model ``optimality error", which explicitly captures the effect of bias and variance in terms of the choice of the pre-scalers. Based on this bound, we identify two solutions of interest: minimum noise variance, and minimum noise variance zero-bias solutions. Numerical evaluations show that using OTA device pre-scalers that minimize the variance of FL updates, while allowing a small bias, can provide high gains over existing schemes. Comment: Accepted at IEEE International Conference on Communications (ICC), 2024 |
نوع الوثيقة: | Working Paper |
URL الوصول: | http://arxiv.org/abs/2403.19849 |
رقم الأكسشن: | edsarx.2403.19849 |
قاعدة البيانات: | arXiv |
الوصف غير متاح. |