Saved in:
Bibliographic Details
Main Authors: Yang, Ziyue, Liu, Feng, Jin, Yifei, Vandikas, Konstantinos
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2511.17841
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915632637804544
author Yang, Ziyue
Liu, Feng
Jin, Yifei
Vandikas, Konstantinos
author_facet Yang, Ziyue
Liu, Feng
Jin, Yifei
Vandikas, Konstantinos
contents This paper presents RadioGUNet, a UNet-based deep learning framework for pathloss estimation in wireless communication. Unlike other frameworks, it leverages group equivariant convolutional networks, which are known to increase the expressive capacity of a neural network by allowing the model to generalize to further classes of symmetries, such as rotations and reflections, without the need for data augmentation or data pre-processing. The results of this work are twofold. First, we show that typical UNet-based convolutional models can be easily extended to support group equivariant convolution (g-conv). Secondly, we show that the task of pathloss estimation benefits from such an extension, as the proposed extended model outperforms typical UNet-based models by up to 0.41 dB for a similar number of parameters in the RadioMapSeer dataset. The code is publicly available on the GitHub page: https://github.com/EricssonResearch/radiogunet
format Preprint
id arxiv_https___arxiv_org_abs_2511_17841
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Group Equivariant Convolutional Networks for Pathloss Estimation
Yang, Ziyue
Liu, Feng
Jin, Yifei
Vandikas, Konstantinos
Networking and Internet Architecture
This paper presents RadioGUNet, a UNet-based deep learning framework for pathloss estimation in wireless communication. Unlike other frameworks, it leverages group equivariant convolutional networks, which are known to increase the expressive capacity of a neural network by allowing the model to generalize to further classes of symmetries, such as rotations and reflections, without the need for data augmentation or data pre-processing. The results of this work are twofold. First, we show that typical UNet-based convolutional models can be easily extended to support group equivariant convolution (g-conv). Secondly, we show that the task of pathloss estimation benefits from such an extension, as the proposed extended model outperforms typical UNet-based models by up to 0.41 dB for a similar number of parameters in the RadioMapSeer dataset. The code is publicly available on the GitHub page: https://github.com/EricssonResearch/radiogunet
title Group Equivariant Convolutional Networks for Pathloss Estimation
topic Networking and Internet Architecture
url https://arxiv.org/abs/2511.17841