Model-based learning for multi-antenna multi-frequency location-to-channel mapping
This work addresses a domain-specific problem in wireless communication for improving channel estimation, but it is incremental as it builds on existing model-based machine learning and INR techniques.
The paper tackled the problem of learning the rapidly varying location-to-channel mapping in multi-antenna multi-frequency systems, which is challenging due to neural networks' spectral bias towards low-frequency content. It proposed a model-based neural architecture derived from a propagation channel model, achieving much better accuracy than classical Implicit Neural Representation architectures on realistic synthetic data.
Years of study of the propagation channel showed a close relation between a location and the associated communication channel response. The use of a neural network to learn the location-to-channel mapping can therefore be envisioned. The Implicit Neural Representation (INR) literature showed that classical neural architecture are biased towards learning low-frequency content, making the location-to-channel mapping learning a non-trivial problem. Indeed, it is well known that this mapping is a function rapidly varying with the location, on the order of the wavelength. This paper leverages the model-based machine learning paradigm to derive a problem-specific neural architecture from a propagation channel model. The resulting architecture efficiently overcomes the spectral-bias issue. It only learns low-frequency sparse correction terms activating a dictionary of high-frequency components. The proposed architecture is evaluated against classical INR architectures on realistic synthetic data, showing much better accuracy. Its mapping learning performance is explained based on the approximated channel model, highlighting the explainability of the model-based machine learning paradigm.