Effector: A Python package for regional explanations
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918199526686720 |
|---|---|
| author | Gkolemis, Vasilis Diou, Christos Kyriakopoulos, Dimitris Tsopelas, Konstantinos Herbinger, Julia Baniecki, Hubert Rontogiannis, Dimitrios Kavouras, Loukas Muschalik, Maximilian Dalamagas, Theodore Ntoutsi, Eirini Bischl, Bernd Casalicchio, Giuseppe |
| author_facet | Gkolemis, Vasilis Diou, Christos Kyriakopoulos, Dimitris Tsopelas, Konstantinos Herbinger, Julia Baniecki, Hubert Rontogiannis, Dimitrios Kavouras, Loukas Muschalik, Maximilian Dalamagas, Theodore Ntoutsi, Eirini Bischl, Bernd Casalicchio, Giuseppe |
| contents | Effector is a Python package for interpreting machine learning (ML) models that are trained on tabular data through global and regional feature effects. Global effects, like Partial Dependence Plot (PDP) and Accumulated Local Effects (ALE), are widely used for explaining tabular ML models due to their simplicity -- each feature's average influence on the prediction is summarized by a single 1D plot. However, when features are interacting, global effects can be misleading. Regional effects address this by partitioning the input space into disjoint subregions with minimal interactions within each and computing a separate regional effect per subspace. Regional effects are then visualized by a set of 1D plots per feature. Effector provides efficient implementations of state-of-the-art global and regional feature effects methods under a unified API. The package integrates seamlessly with major ML libraries like scikit-learn and PyTorch. It is designed to be modular and extensible, and comes with comprehensive documentation and tutorials. Effector is an open-source project publicly available on Github at https://github.com/givasile/effector. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_02629 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Effector: A Python package for regional explanations Gkolemis, Vasilis Diou, Christos Kyriakopoulos, Dimitris Tsopelas, Konstantinos Herbinger, Julia Baniecki, Hubert Rontogiannis, Dimitrios Kavouras, Loukas Muschalik, Maximilian Dalamagas, Theodore Ntoutsi, Eirini Bischl, Bernd Casalicchio, Giuseppe Machine Learning Effector is a Python package for interpreting machine learning (ML) models that are trained on tabular data through global and regional feature effects. Global effects, like Partial Dependence Plot (PDP) and Accumulated Local Effects (ALE), are widely used for explaining tabular ML models due to their simplicity -- each feature's average influence on the prediction is summarized by a single 1D plot. However, when features are interacting, global effects can be misleading. Regional effects address this by partitioning the input space into disjoint subregions with minimal interactions within each and computing a separate regional effect per subspace. Regional effects are then visualized by a set of 1D plots per feature. Effector provides efficient implementations of state-of-the-art global and regional feature effects methods under a unified API. The package integrates seamlessly with major ML libraries like scikit-learn and PyTorch. It is designed to be modular and extensible, and comes with comprehensive documentation and tutorials. Effector is an open-source project publicly available on Github at https://github.com/givasile/effector. |
| title | Effector: A Python package for regional explanations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2404.02629 |