Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks
Safe deployment of graph neural networks (GNNs) under distribution shift requires models to provide accurate confidence indicators (CI). However, while it is well-known in computer vision that CI quality diminishes under distribution shift, this behavior remains understudied for GNNs. Hence, we begin with a case study on CI calibration under controlled structural and feature distribution shifts and demonstrate that increased expressivity or model size do not always lead to improved CI performance. Consequently, we instead advocate for the use of epistemic uncertainty quantification (UQ) methods to modulate CIs. To this end, we propose G-$\Delta$UQ, a new single model UQ method that extends the recently proposed stochastic centering framework to support structured data and partial stochasticity. Evaluated across covariate, concept, and graph size shifts, G-$\Delta$UQ not only outperforms several popular UQ methods in obtaining calibrated CIs, but also outperforms alternatives when CIs are used for generalization gap prediction or OOD detection. Overall, our work not only introduces a new, flexible GNN UQ method, but also provides novel insights into GNN CIs on safety-critical tasks.
Code (0)
등록된 구현이 없습니다.
Tasks
Uncertainty QuantificationSimilar Papers 제목 키워드 기반
Where to Measure: Epistemic Uncertainty-Based Sensor Placement with ConvCNPs
Accurate sensor placement is critical for modeling spatio-temporal systems such as environmental and climate processes. Neural Processes (NPs), particularly Convolutional Conditional Neural Processes (ConvCNPs), provide …
PH-Dropout: Practical Epistemic Uncertainty Quantification for View Synthesis
View synthesis using Neural Radiance Fields (NeRF) and Gaussian Splatting (GS) has demonstrated impressive fidelity in rendering real-world scenarios. However, practical methods for accurate and efficient epistemic Uncer…
NeRFRepresentation LearningUncertainty QuantificationQuantifying Epistemic Uncertainty in Diffusion Models
To ensure high quality outputs, it is important to quantify the epistemic uncertainty of diffusion models. Existing methods are often unreliable because they mix epistemic and aleatoric uncertainty. We introduce a method…
Benchmarking Scalable Epistemic Uncertainty Quantification in Organ Segmentation
Deep learning based methods for automatic organ segmentation have shown promise in aiding diagnosis and treatment planning. However, quantifying and understanding the uncertainty associated with model predictions is cruc…
BenchmarkingMedical Image AnalysisOrgan SegmentationOut-of-Distribution Detection+2Evaluating Scalable Uncertainty Estimation Methods for DNN-Based Molecular Property Prediction
Advances in deep neural network (DNN) based molecular property prediction have recently led to the development of models of remarkable accuracy and generalization ability, with graph convolution neural networks (GCNNs) r…
Bayesian InferenceMolecular Property PredictionProperty PredictionUncertainty Quantification