In machine learning practice it is often useful to identify relevant input features, so as to obtain compact dataset for more efficient numerical handling. On the other hand, by isolating key input elements, ranked according their respective degree of relevance, can help to elaborate on the process of decision making. Here, we propose a novel method to estimate the relative importance of the input components for a Deep Neural Network. This is achieved by leveraging on a spectral re-parametrization of the optimization process. Eigenvalues associated to input nodes provide in fact a robust proxy to gauge the relevance of the supplied entry features. Notably, the spectral features ranking is performed automatically, as a byproduct of the network training, with no additional processing to be carried out. The technique is successfully challenged against both synthetic and real data.
View on arXiv@article{chicchi2025_2406.01183, title={ Automatic Input Feature Relevance via Spectral Neural Networks }, author={ Lorenzo Chicchi and Lorenzo Buffoni and Diego Febbe and Lorenzo Giambagli and Raffaele Marino and Duccio Fanelli }, journal={arXiv preprint arXiv:2406.01183}, year={ 2025 } }