EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Schleibaum, Sören, Thielmann, Anton Frederik, Teusch, Julian, Säfken, Benjamin, Müller, Jörg P.
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915726305001472
author Schleibaum, Sören
Thielmann, Anton Frederik
Teusch, Julian
Säfken, Benjamin
Müller, Jörg P.
author_facet Schleibaum, Sören
Thielmann, Anton Frederik
Teusch, Julian
Säfken, Benjamin
Müller, Jörg P.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08556
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models
Schleibaum, Sören
Thielmann, Anton Frederik
Teusch, Julian
Säfken, Benjamin
Müller, Jörg P.
Machine Learning
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.
title EviNAM: Intelligibility and Uncertainty via Evidential Neural Additive Models
topic Machine Learning
url https://arxiv.org/abs/2601.08556