XpertAI: uncovering regression model strategies for sub-manifolds
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_ | 1866909693807427584 |
|---|---|
| author | Letzgus, Simon Müller, Klaus-Robert Montavon, Grégoire |
| author_facet | Letzgus, Simon Müller, Klaus-Robert Montavon, Grégoire |
| contents | In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g.\ distinguishing between `Why is the output above 0?' and `Why is the output above 50?'). They should furthermore reflect the model's behavior on the relevant data sub-manifold. In this paper, we introduce XpertAI, a framework that disentangles the prediction strategy into multiple range-specific sub-strategies and allows the formulation of precise queries about the model (the `explanandum') as a linear combination of those sub-strategies. XpertAI is formulated generally to work alongside popular XAI attribution techniques, based on occlusion, gradient integration, or reverse propagation. Qualitative and quantitative results, demonstrate the benefits of our approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_07486 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | XpertAI: uncovering regression model strategies for sub-manifolds Letzgus, Simon Müller, Klaus-Robert Montavon, Grégoire Machine Learning In recent years, Explainable AI (XAI) methods have facilitated profound validation and knowledge extraction from ML models. While extensively studied for classification, few XAI solutions have addressed the challenges specific to regression models. In regression, explanations need to be precisely formulated to address specific user queries (e.g.\ distinguishing between `Why is the output above 0?' and `Why is the output above 50?'). They should furthermore reflect the model's behavior on the relevant data sub-manifold. In this paper, we introduce XpertAI, a framework that disentangles the prediction strategy into multiple range-specific sub-strategies and allows the formulation of precise queries about the model (the `explanandum') as a linear combination of those sub-strategies. XpertAI is formulated generally to work alongside popular XAI attribution techniques, based on occlusion, gradient integration, or reverse propagation. Qualitative and quantitative results, demonstrate the benefits of our approach. |
| title | XpertAI: uncovering regression model strategies for sub-manifolds |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2403.07486 |