Group Equivariant Convolutional Networks for Pathloss Estimation
By: Ziyue Yang , Feng Liu , Yifei Jin and more
Potential Business Impact:
Improves wireless signals by teaching computers to see patterns.
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
Similar Papers
Heteroscedastic Neural Networks for Path Loss Prediction with Link-Specific Uncertainty
Machine Learning (CS)
Helps phones predict signal strength better.
Reciprocity-Aware Convolutional Neural Networks for Map-Based Path Loss Prediction
Machine Learning (CS)
Improves phone signal prediction for all directions.
Equivariant-Aware Structured Pruning for Efficient Edge Deployment: A Comprehensive Framework with Adaptive Fine-Tuning
CV and Pattern Recognition
Makes AI models smaller and faster for tricky tasks.