EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models

2026-01-13

AI Summary

Existing methods struggle to simultaneously achieve high interpretability and accurate uncertainty estimation. This work proposes the first integration of evidential deep learning into Neural Additive Models (NAMs), parameterizing predictive uncertainty via Dirichlet distributions to jointly model aleatoric and epistemic uncertainties in a single forward pass while preserving clear interpretability of feature contributions. The approach naturally supports regression, classification, and generalized additive extensions. Empirical evaluations on both synthetic and real-world datasets demonstrate state-of-the-art predictive performance alongside reliable uncertainty quantification and high model interpretability.

Technology Category

• Machine Learning: Calibration & Uncertainty Quantification
• Reasoning under Uncertainty: Relational Probabilistic Models
• Natural Language Processing: Interpretability, Analysis, and Evaluation of NLP Models

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Intelligibility and accurate uncertainty estimation are crucial for reliable decision-making. In this paper, we propose EviNAM, an extension of evidential learning that integrates the interpretability of Neural Additive Models (NAMs) with principled uncertainty estimation. Unlike standard Bayesian neural networks and previous evidential methods, EviNAM enables, in a single pass, both the estimation of the aleatoric and epistemic uncertainty as well as explicit feature contributions. Experiments on synthetic and real data demonstrate that EviNAM matches state-of-the-art predictive performance. While we focus on regression, our method extends naturally to classification and generalized additive models, offering a path toward more intelligible and trustworthy predictions.

Problem

• intelligibility
• uncertainty estimation
• aleatoric uncertainty
• epistemic uncertainty
• interpretable models

Innovation

• Evidential Learning
• Neural Additive Models
• Uncertainty Estimation
• Interpretability
• Aleatoric and Epistemic Uncertainty