← Back to all news
arXiv Machine Learning By Lekun Wang, Jaidev Goel, Yulia R. Gel, Yao Xie

Adaptive Uncertainty Quantification on Simplicial Complexes with Conformalized Simplicial Neural Networks

Read the original on arXiv Machine Learning →

The paper introduces CF‑SNN, a conformalized simplicial neural network framework that provides uncertainty quantification for predictions on simplicial complexes. It generates simultaneous prediction sets for multiple targets, guaranteeing that each set contains the true label with a user‑specified coverage probability. Experiments across diverse SC prediction tasks show that CF‑SNN achieves the desired coverage while keeping prediction sets small and informative.

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 Machine Learning
Oct 12

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.

By Pedro C. Vieira, Viacheslav Borovitskiy, Pedro Ribeiro
computer-visionbenchmarkssafety
More like this →
arXiv Machine Learning
Oct 3

Uncertainty-Aware Learning from Multi-Expert Interval Targets

The paper introduces a method for learning from multiple experts who provide interval labels, addressing both within‑label imprecision and between‑expert variation. It harmonizes diverse label vocabularies into a shared probabilistic space, retains individual intervals using a mixture of Beta distributions, and decomposes predictive uncertainty into components that are matched to their corresponding sources of label uncertainty. On sea‑ice concentration data, the approach achieves a 31% reduction in mean absolute error compared to hard‑label baselines and outperforms several aggregation and interval‑regression methods.

By Samira Alkaee Taleghan, Younghyun Koo, Andrew P. Barrett, Farnoush Banaei-Kashani
More like this →