An Efficient and Explainable KAN Framework for Wireless Radiation Field Prediction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866910001614815232 |
|---|---|
| author | Shen, Jingzhou Wang, Xuyu |
| author_facet | Shen, Jingzhou Wang, Xuyu |
| contents | Modeling wireless channels accurately remains a challenge due to environmental variations and signal uncertainties. Recent neural networks can learn radio frequency~(RF) signal propagation patterns, but they process each voxel on the ray independently, without considering global context or environmental factors. Our paper presents a new approach that learns comprehensive representations of complete rays rather than individual points, capturing more detailed environmental features. We integrate a Kolmogorov-Arnold network (KAN) architecture with transformer modules to achieve better performance across realistic and synthetic scenes while maintaining computational efficiency. Our experimental results show that this approach outperforms existing methods in various scenarios. Ablation studies confirm that each component of our model contributes to its effectiveness. Additional experiments provide clear explanations for our model's performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_11656 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | An Efficient and Explainable KAN Framework for Wireless Radiation Field Prediction Shen, Jingzhou Wang, Xuyu Networking and Internet Architecture Computer Vision and Pattern Recognition Modeling wireless channels accurately remains a challenge due to environmental variations and signal uncertainties. Recent neural networks can learn radio frequency~(RF) signal propagation patterns, but they process each voxel on the ray independently, without considering global context or environmental factors. Our paper presents a new approach that learns comprehensive representations of complete rays rather than individual points, capturing more detailed environmental features. We integrate a Kolmogorov-Arnold network (KAN) architecture with transformer modules to achieve better performance across realistic and synthetic scenes while maintaining computational efficiency. Our experimental results show that this approach outperforms existing methods in various scenarios. Ablation studies confirm that each component of our model contributes to its effectiveness. Additional experiments provide clear explanations for our model's performance. |
| title | An Efficient and Explainable KAN Framework for Wireless Radiation Field Prediction |
| topic | Networking and Internet Architecture Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.11656 |