GLEAMS: Bridging the Gap Between Local and Global 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_ | 1866914906866974720 |
|---|---|
| author | Visani, Giorgio Stanzione, Vincenzo Garreau, Damien |
| author_facet | Visani, Giorgio Stanzione, Vincenzo Garreau, Damien |
| contents | The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these methods require recalculating explanations for each example. On the other side, while there exist global approaches they often produce explanations that are either overly simplistic and unreliable or excessively complex. To bridge this gap, we propose GLEAMS, a novel method that partitions the input space and learns an interpretable model within each sub-region, thereby providing both faithful local and global surrogates. We demonstrate GLEAMS' effectiveness on both synthetic and real-world data, highlighting its desirable properties and human-understandable insights. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_05060 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GLEAMS: Bridging the Gap Between Local and Global Explanations Visani, Giorgio Stanzione, Vincenzo Garreau, Damien Machine Learning Artificial Intelligence The explainability of machine learning algorithms is crucial, and numerous methods have emerged recently. Local, post-hoc methods assign an attribution score to each feature, indicating its importance for the prediction. However, these methods require recalculating explanations for each example. On the other side, while there exist global approaches they often produce explanations that are either overly simplistic and unreliable or excessively complex. To bridge this gap, we propose GLEAMS, a novel method that partitions the input space and learns an interpretable model within each sub-region, thereby providing both faithful local and global surrogates. We demonstrate GLEAMS' effectiveness on both synthetic and real-world data, highlighting its desirable properties and human-understandable insights. |
| title | GLEAMS: Bridging the Gap Between Local and Global Explanations |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2408.05060 |