GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors

Knowledge-extraction methods are applied to ML-based predictors to attain explainable representations of their operation when the lack of interpretable results constitutes a problem. Several algorithms have been proposed for knowledge extraction, mostly focusing on the extraction of either lists or trees of rules. Yet, most of them only support supervised learning – and, in particular, classification – tasks. Iter is among the few rule-extraction methods capable of extracting symbolic rules out of sub-symbolic regressors. However, its performance – here intended as the interpretability of the rules it extracts – easily degrades as the complexity of the regression task at hand increases.

In this paper we propose GridEx, an extension of the Iter algorithm, aimed at extracting symbolic knowledge – in the form of lists of if-then-else rules – from any sort of sub-symbolic regressor—there including neural networks of arbitrary depth. With respect to Iter, GridEx produces shorter rule lists retaining higher fidelity w.r.t. the original regressor. We report several experiments assessing GridEx performance against Iter and Cart (i.e., decision-tree regressors) used as benchmarks.

parole chiave   Explainable AI; Knowledge extraction; Interpretable prediction; Regression; Iter; GridEx

presentazione di riferimento

 GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors (EXTRAAMAS 2021@AAMAS 2021, 03/05/2021) — Federico Sabbatini (Federico Sabbatini, Giovanni Ciatto, Andrea Omicini)

evento origine

 EXTRAAMAS 2021@AAMAS 2021

rivista o collana

 Lecture Notes in Computer Science (LNCS)

progetto finanziatore

 EXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)

 StairwAI — Stairway to AI: Ease the Engagement of Low-Tech users to the AI-on-Demand platform through AI (01/01/2021–31/12/2023)

pubblicazione di riferimento per presentazione

 GridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors (EXTRAAMAS 2021@AAMAS 2021, 03/05/2021) — Federico Sabbatini (Federico Sabbatini, Giovanni Ciatto, Andrea Omicini)