Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916694182592512 |
|---|---|
| author | Fumagalli, Fabian Muschalik, Maximilian Hüllermeier, Eyke Hammer, Barbara Herbinger, Julia |
| author_facet | Fumagalli, Fabian Muschalik, Maximilian Hüllermeier, Eyke Hammer, Barbara Herbinger, Julia |
| contents | Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their applicability for practitioners. In this work, we introduce a unified framework for local and global feature-based explanations using two well-established concepts: functional ANOVA (fANOVA) from statistics, and the notion of value and interaction from cooperative game theory. We introduce three fANOVA decompositions that determine the influence of feature distributions, and use game-theoretic measures, such as the Shapley value and interactions, to specify the influence of higher-order interactions. Our framework combines these two dimensions to uncover similarities and differences between a wide range of explanation techniques for features and groups of features. We then empirically showcase the usefulness of our framework on synthetic and real-world datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17152 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory Fumagalli, Fabian Muschalik, Maximilian Hüllermeier, Eyke Hammer, Barbara Herbinger, Julia Machine Learning Feature-based explanations, using perturbations or gradients, are a prevalent tool to understand decisions of black box machine learning models. Yet, differences between these methods still remain mostly unknown, which limits their applicability for practitioners. In this work, we introduce a unified framework for local and global feature-based explanations using two well-established concepts: functional ANOVA (fANOVA) from statistics, and the notion of value and interaction from cooperative game theory. We introduce three fANOVA decompositions that determine the influence of feature distributions, and use game-theoretic measures, such as the Shapley value and interactions, to specify the influence of higher-order interactions. Our framework combines these two dimensions to uncover similarities and differences between a wide range of explanation techniques for features and groups of features. We then empirically showcase the usefulness of our framework on synthetic and real-world datasets. |
| title | Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theory |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2412.17152 |