Metraipolis › archive › dc_46df1ffa4033
Interval-valued SHAP in Tree-Based Models — arXiv:2610.11953
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.11953
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T06:23:35.173Z
- SHA-256 of the archived text
88a55034ef813aab7be3b3aaa9df40d05fc050ee518dc1b598063dcd79ac7e81- Stable URL of this page
https://metraipolis.com/documento/dc_46df1ffa4033
How to cite
Interval-valued SHAP in Tree-Based Models — arXiv:2610.11953 — arXiv (en), https://arxiv.org/abs/2610.11953 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_46df1ffa4033 (Metraipolis archive dc_46df1ffa4033, sha256 88a55034ef813aab7be3b3aaa9df40d05fc050ee518dc1b598063dcd79ac7e81)
BibTeX
@misc{dc46df1ffa4033,
title = {Interval-valued SHAP in Tree-Based Models — arXiv:2610.11953},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.11953},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_46df1ffa4033; sha256 88a55034ef813aab7be3b3aaa9df40d05fc050ee518dc1b598063dcd79ac7e81},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11953. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Shapley values are among the most popular feature-attribution explanations. Efficient approaches for computing/estimating Shapley values for tree-based models, which are state-of-the-art for tabular data sets, have been developed. However, it is known that Shapley values can be (highly) unrobust due to small and realistic changes. In this paper, we propose an imprecise Dirichlet model (IDM) based method to analyze the robustness of Shapley values in decision trees and random forests. Technically, it is done by quantifying and analyzing the interval-valued Shapley values when a few unannotated instances are randomly introduced to the leaves of the trees. The interval-valued Shapley values can be defined following common principles in handling incomplete data: the pessimistic and averaging principles. We derive various theoretical results that lead to efficient computation of the interval-valued Shapley values. We also show that the proposed method can be straightforwardly generalized to the case of Banzhaf values. We then present various case studies and experiments to illustrate the behaviour of the proposed interval-valued Shapley values and their applications in debiasing uninformative features. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.LG, nuovi lavori del giorno). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2610.11953 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-09T05:50:31.691Z dalla pagina https://arxiv.org/list/cs.LG/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).