Random-Set Graph Neural Networks

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Woodley, Tommy, Manchingal, Shireen Kudukkil, Tolloso, Matteo, Bacciu, Davide, Cuzzolin, Fabio
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913116865953792
author Woodley, Tommy
Manchingal, Shireen Kudukkil
Tolloso, Matteo
Bacciu, Davide
Cuzzolin, Fabio
author_facet Woodley, Tommy
Manchingal, Shireen Kudukkil
Tolloso, Matteo
Bacciu, Davide
Cuzzolin, Fabio
contents Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of the data is a huge mitigating factor to GNN performance. While aleatoric uncertainty is the result of noisy and incomplete stochastic data such as missing edges or over-smoothing, epistemic uncertainty arises from lack of knowledge about a system or model (e.g., a graph's topology or node feature representation), which can be reduced by gathering more data and information. In this paper, we propose an original new framework in which node-level epistemic uncertainty is modelled in a belief function (finite random set) formalism. The resulting Random-Set Graph Neural Networks have a belief-function head predicting a random set over the list of classes, from which both a precise probability prediction and a measure of epistemic uncertainty can be obtained. Extensive experiments on 9 different graph learning datasets, including real-world autonomous driving benchmarks as such Nuscene and ROAD, demonstrate RS-GNN's superior uncertainty quantification capabilities
format Preprint
id arxiv_https___arxiv_org_abs_2605_11987
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Random-Set Graph Neural Networks
Woodley, Tommy
Manchingal, Shireen Kudukkil
Tolloso, Matteo
Bacciu, Davide
Cuzzolin, Fabio
Artificial Intelligence
Machine Learning
Applications
Uncertainty quantification has become an important factor in understanding the data representations produced by Graph Neural Networks (GNNs). Despite their predictive capabilities being ever useful across industrial workspaces, the inherent uncertainty induced by the nature of the data is a huge mitigating factor to GNN performance. While aleatoric uncertainty is the result of noisy and incomplete stochastic data such as missing edges or over-smoothing, epistemic uncertainty arises from lack of knowledge about a system or model (e.g., a graph's topology or node feature representation), which can be reduced by gathering more data and information. In this paper, we propose an original new framework in which node-level epistemic uncertainty is modelled in a belief function (finite random set) formalism. The resulting Random-Set Graph Neural Networks have a belief-function head predicting a random set over the list of classes, from which both a precise probability prediction and a measure of epistemic uncertainty can be obtained. Extensive experiments on 9 different graph learning datasets, including real-world autonomous driving benchmarks as such Nuscene and ROAD, demonstrate RS-GNN's superior uncertainty quantification capabilities
title Random-Set Graph Neural Networks
topic Artificial Intelligence
Machine Learning
Applications
url https://arxiv.org/abs/2605.11987