Logic Explanation of AI Classifiers by Categorical Explaining Functors

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Fioravanti, Stefano, Giannini, Francesco, Frazzetto, Paolo, Zanasi, Fabio, Barbiero, Pietro
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910046722457600
author Fioravanti, Stefano
Giannini, Francesco
Frazzetto, Paolo
Zanasi, Fabio
Barbiero, Pietro
author_facet Fioravanti, Stefano
Giannini, Francesco
Frazzetto, Paolo
Zanasi, Fabio
Barbiero, Pietro
contents The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that account for the mutual interactions of input features in the form of logic rules. However, these methods frequently fail to guarantee the consistency of the extracted explanations with the model's underlying reasoning. To bridge this gap, we propose a theoretically grounded approach to ensure coherence and fidelity of the extracted explanations, moving beyond the limitations of current heuristic-based approaches. To this end, drawing from category theory, we introduce an explaining functor which structurally preserves logical entailment between the explanation and the opaque model's reasoning. As a proof of concept, we validate the proposed theoretical constructions on a synthetic benchmark verifying how the proposed approach significantly mitigates the generation of contradictory or unfaithful explanations.
format Preprint
id arxiv_https___arxiv_org_abs_2503_16203
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Logic Explanation of AI Classifiers by Categorical Explaining Functors
Fioravanti, Stefano
Giannini, Francesco
Frazzetto, Paolo
Zanasi, Fabio
Barbiero, Pietro
Artificial Intelligence
The most common methods in explainable artificial intelligence are post-hoc techniques which identify the most relevant features used by pretrained opaque models. Some of the most advanced post hoc methods can generate explanations that account for the mutual interactions of input features in the form of logic rules. However, these methods frequently fail to guarantee the consistency of the extracted explanations with the model's underlying reasoning. To bridge this gap, we propose a theoretically grounded approach to ensure coherence and fidelity of the extracted explanations, moving beyond the limitations of current heuristic-based approaches. To this end, drawing from category theory, we introduce an explaining functor which structurally preserves logical entailment between the explanation and the opaque model's reasoning. As a proof of concept, we validate the proposed theoretical constructions on a synthetic benchmark verifying how the proposed approach significantly mitigates the generation of contradictory or unfaithful explanations.
title Logic Explanation of AI Classifiers by Categorical Explaining Functors
topic Artificial Intelligence
url https://arxiv.org/abs/2503.16203