midr: Learning from Black-Box Models by Maximum Interpretation Decomposition
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912422389874688 |
|---|---|
| author | Asashiba, Ryoichi Kozuma, Reiji Iwasawa, Hirokazu |
| author_facet | Asashiba, Ryoichi Kozuma, Reiji Iwasawa, Hirokazu |
| contents | The use of appropriate methods of Interpretable Machine Learning (IML) and eXplainable Artificial Intelligence (XAI) is essential for adopting black-box predictive models in fields where model and prediction explainability is required. As a novel tool for interpreting black-box models, we introduce the R package midr, which implements Maximum Interpretation Decomposition (MID). MID is a functional decomposition approach that derives a low-order additive representation of a black-box model by minimizing the squared error between the model's prediction function and this additive representation. midr enables learning from black-box models by constructing a global surrogate model with advanced analytical capabilities. After reviewing related work and the theoretical foundation of MID, we demonstrate the package's usage and discuss some of its key features. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_08338 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | midr: Learning from Black-Box Models by Maximum Interpretation Decomposition Asashiba, Ryoichi Kozuma, Reiji Iwasawa, Hirokazu Methodology Machine Learning The use of appropriate methods of Interpretable Machine Learning (IML) and eXplainable Artificial Intelligence (XAI) is essential for adopting black-box predictive models in fields where model and prediction explainability is required. As a novel tool for interpreting black-box models, we introduce the R package midr, which implements Maximum Interpretation Decomposition (MID). MID is a functional decomposition approach that derives a low-order additive representation of a black-box model by minimizing the squared error between the model's prediction function and this additive representation. midr enables learning from black-box models by constructing a global surrogate model with advanced analytical capabilities. After reviewing related work and the theoretical foundation of MID, we demonstrate the package's usage and discuss some of its key features. |
| title | midr: Learning from Black-Box Models by Maximum Interpretation Decomposition |
| topic | Methodology Machine Learning |
| url | https://arxiv.org/abs/2506.08338 |