On the Robustness of Global Feature Effect Explanations
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909707112808448 |
|---|---|
| author | Baniecki, Hubert Casalicchio, Giuseppe Bischl, Bernd Biecek, Przemyslaw |
| author_facet | Baniecki, Hubert Casalicchio, Giuseppe Bischl, Bernd Biecek, Przemyslaw |
| contents | We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09069 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On the Robustness of Global Feature Effect Explanations Baniecki, Hubert Casalicchio, Giuseppe Bischl, Bernd Biecek, Przemyslaw Machine Learning We study the robustness of global post-hoc explanations for predictive models trained on tabular data. Effects of predictor features in black-box supervised learning are an essential diagnostic tool for model debugging and scientific discovery in applied sciences. However, how vulnerable they are to data and model perturbations remains an open research question. We introduce several theoretical bounds for evaluating the robustness of partial dependence plots and accumulated local effects. Our experimental results with synthetic and real-world datasets quantify the gap between the best and worst-case scenarios of (mis)interpreting machine learning predictions globally. |
| title | On the Robustness of Global Feature Effect Explanations |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2406.09069 |