Score: 1

Group Equivariant Convolutional Networks for Pathloss Estimation

Published: November 21, 2025 | arXiv ID: 2511.17841v1

By: Ziyue Yang , Feng Liu , Yifei Jin and more

Potential Business Impact:

Improves wireless signals by teaching computers to see patterns.

Business Areas:
Darknet Internet Services

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

Country of Origin
πŸ‡ΈπŸ‡ͺ Sweden

Repos / Data Links

Page Count
5 pages

Category
Computer Science:
Networking and Internet Architecture