← Back to all news
arXiv Machine Learning By Pedro C. Vieira, Viacheslav Borovitskiy, Pedro Ribeiro

Do Deep Ensembles Actually Capture Uncertainty in Graph Neural Networks?

Read the original on arXiv Machine Learning →

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

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 →