Byaproperscalingofthedistance, ourproposed Maximum Concept Matching (MCM) scoreachievesstrong ID-OODseparability (see Figure 1). Thereexistsoverlappingregions (shown w); Right: Cosinesimilaritiesbetween OODinIDconceptvectors.

However,GNNs have notconsidered different types ofuncertainties associated with class probabilities to minimize risk of increasing misclassification under uncertainty in real life. In this work, we propose a multi-source uncertainty framework using a GNN that reflects various types of predictive uncertainties in both deep learning and belief/evidence theory domains fornodeclassification predictions.

Unsupervised out-of-distribution (OOD) detection is essential for the reliability ofmachine learning. Inthe literature, existing work has shown that higher-level semantics captured by hierarchical VAEs can be used to detect OOD instances.

When question "Is isthe training?"We Weshow FPR95 (left) and AUROC (right).