Random-Set Graph Neural Networks
Not on the map. Why?
Abstract (arXiv)
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
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 63 of its 107 references that are in the map. First posted on arXiv 12 May 2026.
Builds on
63 of 107 references.
References · 63
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2017On Calibration of Modern Neural Networkscited by 4,960
- 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
- 2020Open Graph Benchmark: Datasets for Machine Learning on Graphscited by 2,163
- 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
- 2017Enhancing The Reliability of Out-of-distribution Image Detection in Neural Networkscited by 1,328
- 2020Energy-based Out-of-distribution Detectioncited by 1,299
- 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,287
- 2018Pitfalls of Graph Neural Network Evaluationcited by 1,007
38 more
- 2016Revisiting Semi-Supervised Learning with Graph Embeddingscited by 976
- 2019Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methodscited by 913
- 2021How Attentive are Graph Attention Networks?cited by 835
- 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
- 2021A Survey of Uncertainty in Deep Neural Networkscited by 680
- 2022Out-of-Distribution Detection with Deep Nearest Neighborscited by 600
- 2018Predictive Uncertainty Estimation via Prior Networkscited by 557
- 2019Multi-scale Attributed Node Embeddingcited by 548
- 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 343
- 2021Large Scale Learning on Non-Homophilous Graphs: New Benchmarks and Strong Simple Methodscited by 311
- 2019Evaluating Scalable Bayesian Deep Learning Methods for Robust Computer Visioncited by 182
- 2020Bayesian Neural Networks: An Introduction and Surveycited by 131
- 2019A Gentle Introduction to Deep Learning for Graphscited by 108
- 2020Uncertainty Aware Semi-Supervised Learning on Graph Datacited by 95
- 2021Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibrationcited by 92
- 2022A Deeper Look into Aleatoric and Epistemic Uncertainty Disentanglementcited by 87
- 2020Bayesian Graph Neural Networks with Adaptive Connection Samplingcited by 81
- 2021Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classificationcited by 80
- 2023Energy-based Out-of-Distribution Detection for Graph Neural Networkscited by 68
- 2022Deep Ensembles Work, But Are They Necessary?cited by 63
- 2021ROAD: The ROad event Awareness Dataset for Autonomous Drivingcited by 54
- 2023Is the Volume of a Credal Set a Good Measure for Epistemic Uncertainty?cited by 40
- 2024Credal Learning Theorycited by 31
- 2024CreINNs: Credal-Set Interval Neural Networks for Uncertainty Estimation in Classification Taskscited by 26
- 2024Uncertainty in Graph Neural Networks: A Surveycited by 23
- 2023Random-Set Neural Networks (RS-NN)cited by 19
- 2022Epistemic Deep Learningcited by 15
- 2024Energy-based Epistemic Uncertainty for Graph Neural Networkscited by 14
- 2018Visions of a generalized probability theorycited by 13
- 2022Towards OOD Detection in Graph Classification from Uncertainty Estimation Perspectivecited by 13
- 2022A General Framework for quantifying Aleatoric and Epistemic uncertainty in Graph Neural Networkscited by 12
- 2013Decision under Uncertaintycited by 11
- 2020Efficient Computation Reduction in Bayesian Neural Networks Through Feature Decomposition and Memorizationcited by 10
- 2022Deep-Ensemble-Based Uncertainty Quantification in Spatiotemporal Graph Neural Networks for Traffic Forecastingcited by 10
- 2023Graph Neural Network Interatomic Potential Ensembles with Calibrated Aleatoric and Epistemic Uncertainty on Energy and Forcescited by 10
- 2025A Unified Evaluation Framework for Epistemic Predictionscited by 10
- 2021Uncertainty measures: The big picturecited by 8
- 2025Credal and Interval Deep Evidential Classificationscited by 8
50 most cited of 63 All 63 (JSON)
Built on by
Citing papers per year: 2026: 3.
3 papers.