Interpreting Deep Forest through Feature Contribution and MDI Feature Importance
ACM Transactions on Knowledge Discovery from Data · 30.11.2025 · 20 (1) · 1-21
DOI: 10.1145/3641108 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Knowledge Discovery from Data, online erschienen am 11.12.2025. Verfasst von Yi-Xiao He und 2 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Jiangsu Science Foundation, China Postdoctoral Science Foundation.
Abstract (Originalsprache)
Deep forest is a non-differentiable deep model that has achieved impressive empirical success across a wide variety of applications, especially on categorical/symbolic or mixed modeling tasks. Many of the application fields prefer explainable models, such as random forests with feature contributions that can provide a local explanation for each prediction, and Mean Decrease Impurity (MDI) that can provide global feature importance. However, deep forest, as a cascade of random forests, possesses interpretability only at the first layer. From the second layer on, many of the tree splits occur on the new features generated by the previous layer, which makes existing explaining tools for random forests inapplicable. To disclose the impact of the original features in the deep layers, we design a calculation method with an estimation step followed by a calibration step for each layer, and propose our feature contribution and MDI feature importance calculation tools for deep forest. Experimental results on both simulated data and real-world data verify the effectiveness of our methods.
Förderung
- National Natural Science Foundation of China
- Jiangsu Science Foundation
- China Postdoctoral Science Foundation
- Jiangsu Excellent Postdoctoral Program
- Collaborative Innovation Center of Novel Software Technology and Industrialization
Zitieren
APA
He, Y., Lyu, S., & Jiang, Y. (2025). Interpreting Deep Forest through Feature Contribution and MDI Feature Importance. ACM Transactions on Knowledge Discovery from Data, 20(1), 1-21. https://doi.org/10.1145/3641108
Vancouver
He Y, Lyu S, Jiang Y. Interpreting Deep Forest through Feature Contribution and MDI Feature Importance. ACM Transactions on Knowledge Discovery from Data. 2025;20(1):1-21. doi:10.1145/3641108
BibTeX
@article{He2025,
author = {He, Yi-Xiao and Lyu, Shen-Huan and Jiang, Yuan},
title = {Interpreting Deep Forest through Feature Contribution and MDI Feature Importance},
journal = {ACM Transactions on Knowledge Discovery from Data},
year = {2025},
volume = {20},
number = {1},
pages = {1--21},
doi = {10.1145/3641108}
}
EUVIMED