The Susceptibility of Example-Based Explainability Methods to Class Outliers
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917738503471104 |
|---|---|
| author | Nematov, Ikhtiyor Sacharidis, Dimitris Sagi, Tomer Hose, Katja |
| author_facet | Nematov, Ikhtiyor Sacharidis, Dimitris Sagi, Tomer Hose, Katja |
| contents | This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as correctness and relevance, specifically for example-based methods, and introduce a new metric, distinguishability. Using these metrics, we highlight the shortcomings of current example-based explainability methods, including those who attempt to suppress class outliers. We conduct experiments on two datasets, a text classification dataset and an image classification dataset, and evaluate the performance of four state-of-the-art explainability methods. Our findings underscore the need for robust techniques to tackle the challenges posed by class outliers. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_20678 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Susceptibility of Example-Based Explainability Methods to Class Outliers Nematov, Ikhtiyor Sacharidis, Dimitris Sagi, Tomer Hose, Katja Machine Learning This study explores the impact of class outliers on the effectiveness of example-based explainability methods for black-box machine learning models. We reformulate existing explainability evaluation metrics, such as correctness and relevance, specifically for example-based methods, and introduce a new metric, distinguishability. Using these metrics, we highlight the shortcomings of current example-based explainability methods, including those who attempt to suppress class outliers. We conduct experiments on two datasets, a text classification dataset and an image classification dataset, and evaluate the performance of four state-of-the-art explainability methods. Our findings underscore the need for robust techniques to tackle the challenges posed by class outliers. |
| title | The Susceptibility of Example-Based Explainability Methods to Class Outliers |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2407.20678 |