Szczegóły publikacji
Opis bibliograficzny
Towards explainability of tree-based ensemble models : a critical overview / Dominik SEPIOŁO, Antoni LIGĘZA // W: New advances in dependability of networks and systems : proceedings of the Seventeenth International Conference on Dependability of Computer Systems DepCoS-RELCOMEX : June 27 – July 1, 2022, Wrocław, Poland / eds. Wojciech Zamojski, [et al.]. — Cham : Springer Nature Switzerland, cop. 2022. — (Lecture Notes in Networks and Systems ; ISSN 2367-3370 ; vol. 484). — ISBN: 978-3-031-06745-7; e-ISBN: 978-3-031-06746-4. — S. 287–296. — Bibliogr., Abstr. — Publikacja dostępna online od: 2022-05-27
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 140624 |
|---|---|
| Data dodania do BaDAP | 2022-06-21 |
| DOI | 10.1007/978-3-031-06746-4_28 |
| Rok publikacji | 2022 |
| Typ publikacji | materiały konferencyjne (aut.) |
| Otwarty dostęp |  |
| Wydawca | Springer |
| Czasopismo/seria | Lecture Notes in Networks and Systems |
Abstract
Tree-based ensemble models are widely applied in artificial intelligence systems due to their robustness and generality. However, those models are not transparent. For the sake of making systems trustworthy and dependable, multiple explanation techniques are developed. This paper presents selected explainability techniques for tree-based ensemble models. First, the aspect of black-boxness and the definition of explainability are reported. Then, predominant model-agnostic (LIME, SHAP, counterfactual explanations), as well as model-specific techniques (fusion into a single decision tree, iForest) are described. Moreover, other methods are also briefly mentioned. Finally, a brief summary is presented.
