CUQ-GNN: Committee-Based Graph Uncertainty Quantification Using Posterior Networks

Damke, Clemens und Hüllermeier, Eyke (September 2024): CUQ-GNN: Committee-Based Graph Uncertainty Quantification Using Posterior Networks. European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2024), Vilnius, Lithuania, 9. - 13. September 2024. In: Machine Learning and Knowledge Discovery in Databases Part VIII, Proc. ECML PKDD 2024, LNCS Vol. 14948 Cham: Springer. pp. 306-323

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 (PPR) 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 (GNNs) 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.

• Item Type: Conference or Workshop Item (Paper)
• Keywords: uncertainty quantification, graph neural networks
• Faculties: Mathematics, Computer Science and Statistics > Computer Science > Artificial Intelligence and Machine Learning
• Subjects: 000 Computer science, information and general works > 004 Data processing computer science
• ISBN: 978-3-031-70370-6
• ISSN: 0302-9743
• Place of Publication: Cham
• Language: English