BayesNAM: Leveraging Inconsistency for Reliable Explanations
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_ | 1866913575469056000 |
|---|---|
| author | Kim, Hoki Park, Jinseong Choi, Yujin Lee, Seungyun Lee, Jaewook |
| author_facet | Kim, Hoki Park, Jinseong Choi, Yujin Lee, Seungyun Lee, Jaewook |
| contents | Neural additive model (NAM) is a recently proposed explainable artificial intelligence (XAI) method that utilizes neural network-based architectures. Given the advantages of neural networks, NAMs provide intuitive explanations for their predictions with high model performance. In this paper, we analyze a critical yet overlooked phenomenon: NAMs often produce inconsistent explanations, even when using the same architecture and dataset. Traditionally, such inconsistencies have been viewed as issues to be resolved. However, we argue instead that these inconsistencies can provide valuable explanations within the given data model. Through a simple theoretical framework, we demonstrate that these inconsistencies are not mere artifacts but emerge naturally in datasets with multiple important features. To effectively leverage this information, we introduce a novel framework, Bayesian Neural Additive Model (BayesNAM), which integrates Bayesian neural networks and feature dropout, with theoretical proof demonstrating that feature dropout effectively captures model inconsistencies. Our experiments demonstrate that BayesNAM effectively reveals potential problems such as insufficient data or structural limitations of the model, providing more reliable explanations and potential remedies. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_06367 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | BayesNAM: Leveraging Inconsistency for Reliable Explanations Kim, Hoki Park, Jinseong Choi, Yujin Lee, Seungyun Lee, Jaewook Machine Learning Artificial Intelligence Neural and Evolutionary Computing Neural additive model (NAM) is a recently proposed explainable artificial intelligence (XAI) method that utilizes neural network-based architectures. Given the advantages of neural networks, NAMs provide intuitive explanations for their predictions with high model performance. In this paper, we analyze a critical yet overlooked phenomenon: NAMs often produce inconsistent explanations, even when using the same architecture and dataset. Traditionally, such inconsistencies have been viewed as issues to be resolved. However, we argue instead that these inconsistencies can provide valuable explanations within the given data model. Through a simple theoretical framework, we demonstrate that these inconsistencies are not mere artifacts but emerge naturally in datasets with multiple important features. To effectively leverage this information, we introduce a novel framework, Bayesian Neural Additive Model (BayesNAM), which integrates Bayesian neural networks and feature dropout, with theoretical proof demonstrating that feature dropout effectively captures model inconsistencies. Our experiments demonstrate that BayesNAM effectively reveals potential problems such as insufficient data or structural limitations of the model, providing more reliable explanations and potential remedies. |
| title | BayesNAM: Leveraging Inconsistency for Reliable Explanations |
| topic | Machine Learning Artificial Intelligence Neural and Evolutionary Computing |
| url | https://arxiv.org/abs/2411.06367 |