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

   page       attach   

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.

evento contenitore
worldEXTRAAMAS 2021@AAMAS 2021
pubblicazione di riferimento
page_white_acrobatGridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors (articolo in atti, 2021) — Federico Sabbatini, Giovanni Ciatto, Andrea Omicini
progetto finanziatore
wrenchEXPECTATION — Personalized Explainable Artificial Intelligence for decentralized agents with heterogeneous knowledge (01/04/2021–31/03/2024)
wrenchStairwAI — Stairway to AI: Ease the Engagement of Low-Tech users to the AI-on-Demand platform through AI (01/01/2021–31/12/2023)
funge da
presentazione di riferimento per
page_white_acrobatGridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors (articolo in atti, 2021) — Federico Sabbatini, Giovanni Ciatto, Andrea Omicini