X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918357108785152 |
|---|---|
| author | Gizzini, Abdul Karim Medjahdi, Yahia |
| author_facet | Gizzini, Abdul Karim Medjahdi, Yahia |
| contents | AI-native architectures are vital for 6G wireless communications. The black-box nature and high complexity of deep learning models employed in critical applications, such as channel estimation, limit their practical deployment. While perturbation-based XAI solutions offer input filtering, they often neglect internal structural optimization. We propose X-REFINE, an XAI-based framework for joint input-filtering and architecture fine-tuning. By utilizing a decomposition-based, sign-stabilized LRP epsilon rule, X-REFINE backpropagates predictions to derive high-resolution relevance scores for both subcarriers and hidden neurons. This enables a holistic optimization that identifies the most faithful model components. Simulation results demonstrate that X-REFINE achieves a superior interpretability-performance-complexity trade-off, significantly reducing computational complexity while maintaining robust bit error rate (BER) performance across different scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_22277 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation Gizzini, Abdul Karim Medjahdi, Yahia Machine Learning Signal Processing AI-native architectures are vital for 6G wireless communications. The black-box nature and high complexity of deep learning models employed in critical applications, such as channel estimation, limit their practical deployment. While perturbation-based XAI solutions offer input filtering, they often neglect internal structural optimization. We propose X-REFINE, an XAI-based framework for joint input-filtering and architecture fine-tuning. By utilizing a decomposition-based, sign-stabilized LRP epsilon rule, X-REFINE backpropagates predictions to derive high-resolution relevance scores for both subcarriers and hidden neurons. This enables a holistic optimization that identifies the most faithful model components. Simulation results demonstrate that X-REFINE achieves a superior interpretability-performance-complexity trade-off, significantly reducing computational complexity while maintaining robust bit error rate (BER) performance across different scenarios. |
| title | X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation |
| topic | Machine Learning Signal Processing |
| url | https://arxiv.org/abs/2602.22277 |