X-REFINE: XAI-based RElevance input-Filtering and archItecture fiNe-tuning for channel Estimation
This work addresses the practical deployment challenges of AI models in 6G wireless communications, offering an incremental improvement by integrating input filtering and architecture fine-tuning.
The paper tackles the problem of deploying deep learning models for channel estimation in 6G wireless communications by addressing their black-box nature and high complexity, proposing X-REFINE, an XAI-based framework that achieves a superior interpretability-performance-complexity trade-off, significantly reducing computational complexity while maintaining robust bit error rate performance.
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.