Neural Interpretable Reasoning
Machine Learning
2025-03-05 v2 Artificial Intelligence
Neural and Evolutionary Computing
Abstract
We formalize a novel modeling framework for achieving interpretability in deep learning, anchored in the principle of inference equivariance. While the direct verification of interpretability scales exponentially with the number of variables of the system, we show that this complexity can be mitigated by treating interpretability as a Markovian property and employing neural re-parametrization techniques. Building on these insights, we propose a new modeling paradigm -- neural generation and interpretable execution -- that enables scalable verification of equivariance. This paradigm provides a general approach for designing Neural Interpretable Reasoners that are not only expressive but also transparent.
Cite
@article{arxiv.2502.11639,
title = {Neural Interpretable Reasoning},
author = {Pietro Barbiero and Giuseppe Marra and Gabriele Ciravegna and David Debot and Francesco De Santis and Michelangelo Diligenti and Mateo Espinosa Zarlenga and Francesco Giannini},
journal= {arXiv preprint arXiv:2502.11639},
year = {2025}
}