← Back to all news
arXiv Machine Learning

Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?

The paper examines whether deep ensembles effectively capture uncertainty in message‑passing graph neural networks. Across eight diverse datasets, ensembles only marginally outperform single models, mainly by reducing optimization noise rather than improving uncertainty estimates. The authors identify an epistemic collapse—independently trained networks converge to similar predictions—due to the smoothing bias of message passing, and provide a theoretical bound linking this collapse to graph topology and Dirichlet energy.

Related stories

arXiv AI
Oct 5

Rethinking Epistemic Uncertainty in Node Classification through Information Growth

The paper introduces a statistical framework to test whether epistemic uncertainty in node classification decreases as more information about the data‑generating process becomes available. It shows that existing graph evidential deep learning methods fail to meet a consistency criterion under this framework, because they regulate uncertainty via hyperparameters rather than data uncertainty. The authors propose graph bootstrap ensembles, which reduce epistemic uncertainty more effectively than standard deep ensembles and satisfy the consistency criterion in controlled experiments.

By Emma Meneghini, Francesco Ferrini, Bruno Lepri, Andrea Passerini, Veronica Lachi
More like this →
arXiv Machine Learning
Aug 24

Hidden Axis of Uncertainty: Latent-Posterior Alignment in Graph Neural Networks with Bayesian Output Layers

The paper introduces Latent-Posterior Alignment (LPA), a phenomenon where predictive uncertainty in Graph Neural Networks with Bayesian output layers decreases as latent representations align with lower‑variance posterior directions, even without posterior variance contraction. Through interventional experiments, the authors demonstrate LPA’s functional role in shaping uncertainty and propose Alignment‑Guided Learning (AGL) to explicitly promote this alignment during training. AGL reduces predictive uncertainty, preserves accuracy, and improves structural calibration, ensuring model confidence reflects data density.

By Suk Hoon Choi, Damdae Park, Junhyuk Choi, Hyein Jung, Changsoo Kim, Ung Lee, Kyeongsu Kim
safety
More like this →
arXiv Machine Learning
Oct 7

Uncertainty Quantification Is Indispensable for Reliable Connectome-Based Graph Learning: A Narrative Review and Case Study

The paper reviews uncertainty quantification (UQ) methods for graph neural networks used in connectome-based diagnostic classification and presents a case study on a temporal Graph Attention Network applied to dynamic functional connectivity data for Cocaine Use Disorder. It highlights that deterministic GNNs can produce overconfident predictions, as shown by a Monte Carlo dropout audit revealing high confidence on misclassified subjects. The study demonstrates the need for rigorous UQ, calibration, and selective prediction to ensure reliable graph-based biomarkers in clinical neuroscience.

By Mansooreh Pakravan
computer-vision
More like this →
arXiv Machine Learning
Aug 26

Multi-Source Complex Network Reconstruction via Wasserstein Distributionally Robust Optimization and Algorithm Unrolling

The paper introduces MS‑WDRO, a multi‑source Wasserstein distributionally robust optimization framework for reconstructing complex network topologies from scarce target‑domain data and abundant heterogeneous source data. It fuses sources via a weighted Wasserstein barycenter, builds an ambiguity set around it, and solves a regularized Laplacian estimator using a provably convergent ADMM scheme. The authors provide finite‑sample guarantees, demonstrate that naive aggregation is suboptimal, and show through experiments on synthetic data and the ABIDE I neuroimaging dataset that MS‑WDRO outperforms seven baselines in graph recovery, sample efficiency, and diagnostic utility, especially when target samples are limited.

By Chuansen Peng, Yifan Xia, Jinshan Zhong, Xiaojing Shen
efficiencybenchmarkssafety
More like this →