BayesNAM: Leveraging Inconsistency for Reliable Explanations
Hoki Kima b, J.-G. Parkb, Yujin Choib, Seungyun Leeb, Jaewook Leeb
- aDepartment of Industrial Engineering , Seoul National University , South Korea
- bDepartment of Industrial Security , Chung-Ang University , South Korea
Papers open inside SciRah from the original publisher or repository; SciRah never hosts them.
Abstract
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.
TL;DRA novel framework, Bayesian Neural Additive Model (BayesNAM), is introduced, which integrates Bayesian neural networks and feature dropout, with theoretical proof demonstrating that feature dropout effectively captures model inconsistencies. (Semantic Scholar)