Contributo in atti di convegno, 2023, ENG, 10.48786/edbt.2023.14

GAM Forest explanation

Lucchese C.; Orlando S.; Perego R.; Veneri A.

Ca' Foscari University of Venice, Venice, Italy; Ca' Foscari University of Venice, Venice, Italy; CNR-ISTI, Pisa, Italy; CNR-ISTI, Pisa, Italy

Most accurate machine learning models unfortunately produce black-box predictions, for which it is impossible to grasp the internal logic that leads to a specific decision. Unfolding the logic of such black-box models is of increasing importance, especially when they are used in sensitive decision-making processes. In thisworkwe focus on forests of decision trees, which may include hundreds to thousands of decision trees to produce accurate predictions. Such complexity raises the need of developing explanations for the predictions generated by large forests.We propose a post hoc explanation method of large forests, named GAM-based Explanation of Forests (GEF), which builds a Generalized Additive Model (GAM) able to explain, both locally and globally, the impact on the predictions of a limited set of features and feature interactions.We evaluate GEF over both synthetic and real-world datasets and show that GEF can create a GAM model with high fidelity by analyzing the given forest only and without using any further information, not even the initial training dataset.

EDBT 2022 - 26th International Conference on Extending Database Technology, pp. 171–182, Ioannina, Greece, 28-31/03/2023

Keywords

Artificial intelligence, Explainability

CNR authors

Veneri Alberto, Perego Raffaele

CNR institutes

ISTI – Istituto di scienza e tecnologie dell'informazione "Alessandro Faedo"

ID: 471663

Year: 2023

Type: Contributo in atti di convegno

Creation: 2022-10-04 16:11:49.000

Last update: 2022-10-11 11:42:36.000

External IDs

CNR OAI-PMH: oai:it.cnr:prodotti:471663

DOI: 10.48786/edbt.2023.14

Scopus: 2-s2.0-85137610939