A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866929402370064384 |
|---|---|
| author | Salih, Ahmed Raisi-Estabragh, Zahra Galazzo, Ilaria Boscolo Radeva, Petia Petersen, Steffen E. Menegaz, Gloria Lekadir, Karim |
| author_facet | Salih, Ahmed Raisi-Estabragh, Zahra Galazzo, Ilaria Boscolo Radeva, Petia Petersen, Steffen E. Menegaz, Gloria Lekadir, Karim |
| contents | eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framework for interpretation of their outputs, highlighting their weaknesses and strengths. Specifically, we discuss their outcomes in terms of model-dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction). The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2305_02012 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME Salih, Ahmed Raisi-Estabragh, Zahra Galazzo, Ilaria Boscolo Radeva, Petia Petersen, Steffen E. Menegaz, Gloria Lekadir, Karim Machine Learning Artificial Intelligence eXplainable artificial intelligence (XAI) methods have emerged to convert the black box of machine learning (ML) models into a more digestible form. These methods help to communicate how the model works with the aim of making ML models more transparent and increasing the trust of end-users into their output. SHapley Additive exPlanations (SHAP) and Local Interpretable Model Agnostic Explanation (LIME) are two widely used XAI methods, particularly with tabular data. In this perspective piece, we discuss the way the explainability metrics of these two methods are generated and propose a framework for interpretation of their outputs, highlighting their weaknesses and strengths. Specifically, we discuss their outcomes in terms of model-dependency and in the presence of collinearity among the features, relying on a case study from the biomedical domain (classification of individuals with or without myocardial infarction). The results indicate that SHAP and LIME are highly affected by the adopted ML model and feature collinearity, raising a note of caution on their usage and interpretation. |
| title | A Perspective on Explainable Artificial Intelligence Methods: SHAP and LIME |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2305.02012 |