English

CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks

Machine Learning 2024-09-09 v1 Machine Learning

Abstract

In this work, we study the influence of domain-specific characteristics when defining a meaningful notion of predictive uncertainty on graph data. Previously, the so-called Graph Posterior Network (GPN) model has been proposed to quantify uncertainty in node classification tasks. Given a graph, it uses Normalizing Flows (NFs) to estimate class densities for each node independently and converts those densities into Dirichlet pseudo-counts, which are then dispersed through the graph using the personalized Page-Rank algorithm. The architecture of GPNs is motivated by a set of three axioms on the properties of its uncertainty estimates. We show that those axioms are not always satisfied in practice and therefore propose the family of Committe-based Uncertainty Quantification Graph Neural Networks (CUQ-GNNs), which combine standard Graph Neural Networks with the NF-based uncertainty estimation of Posterior Networks (PostNets). This approach adapts more flexibly to domain-specific demands on the properties of uncertainty estimates. We compare CUQ-GNN against GPN and other uncertainty quantification approaches on common node classification benchmarks and show that it is effective at producing useful uncertainty estimates.

Keywords

Cite

@article{arxiv.2409.04159,
  title  = {CUQ-GNN: Committee-based Graph Uncertainty Quantification using Posterior Networks},
  author = {Clemens Damke and Eyke Hüllermeier},
  journal= {arXiv preprint arXiv:2409.04159},
  year   = {2024}
}

Comments

17 pages, 4 figures, 1 table. Accepted at ECML PKDD 2024. arXiv admin note: substantial text overlap with arXiv:2406.04041

R2 v1 2026-06-28T18:36:18.859Z