SOURCE-LINKED INTELLIGENCE

Online Bayesian Node Classification on Inductive Graphs under Distribution Shift

arXiv · AI, language, vision and robotics · article · Sep 12, 2026 · UTC

On evolving graphs, node classifiers must satisfy two key requirements: inductive generalization to newly arriving nodes under distribution shift and calibrated uncertainty for safety-sensitive applications. Standard graph neural networks (GNNs) are typically trained once and address neither requirement. We adapt the Bayesian last-layer (BLL) model by placing random last-layer parameters on top of a deterministic GNN encoder for uncertainty quantification. The categorical softmax likelihood required for classification breaks Gaussian conjugacy, so neither the training posterior nor the test-ti

Read original source ↗ Open in workspace

recordType

paper

region

Global