Foundations of Interpretable Models
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866916875187781632 |
|---|---|
| author | Barbiero, Pietro Zarlenga, Mateo Espinosa Termine, Alberto Jamnik, Mateja Marra, Giuseppe |
| author_facet | Barbiero, Pietro Zarlenga, Mateo Espinosa Termine, Alberto Jamnik, Mateja Marra, Giuseppe |
| contents | We argue that existing definitions of interpretability are not actionable in that they fail to inform users about general, sound, and robust interpretable model design. This makes current interpretability research fundamentally ill-posed. To address this issue, we propose a definition of interpretability that is general, simple, and subsumes existing informal notions within the interpretable AI community. We show that our definition is actionable, as it directly reveals the foundational properties, underlying assumptions, principles, data structures, and architectural features necessary for designing interpretable models. Building on this, we propose a general blueprint for designing interpretable models and introduce the first open-sourced library with native support for interpretable data structures and processes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_00545 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foundations of Interpretable Models Barbiero, Pietro Zarlenga, Mateo Espinosa Termine, Alberto Jamnik, Mateja Marra, Giuseppe Machine Learning Artificial Intelligence Neural and Evolutionary Computing We argue that existing definitions of interpretability are not actionable in that they fail to inform users about general, sound, and robust interpretable model design. This makes current interpretability research fundamentally ill-posed. To address this issue, we propose a definition of interpretability that is general, simple, and subsumes existing informal notions within the interpretable AI community. We show that our definition is actionable, as it directly reveals the foundational properties, underlying assumptions, principles, data structures, and architectural features necessary for designing interpretable models. Building on this, we propose a general blueprint for designing interpretable models and introduce the first open-sourced library with native support for interpretable data structures and processes. |
| title | Foundations of Interpretable Models |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2508.00545 |