analiza aiqbench
The paper proposes CF-SNN, a conformal prediction method that adds statistical coverage guarantees to simplicial neural networks, which operate on higher-order relational data. The coverage guarantees are the main contribution, and the authors claim they hold across multiple prediction targets. Readers should note that the results come from the authors' experiments on a range of tasks, so practical performance will depend on the datasets and assumptions involved.
Adaptive Uncertainty Quantification on Simplicial Complexes with Conformalized Simplicial Neural Networks
arXiv:2610.41166v1 Announce Type: cross Abstract: Simplicial neural networks (SNNs) are powerful tools for prediction tasks on higher-order relational datasets stored on simplicial complexes (SCs), a higher-order generalization of graphs. However, SNNs usually lack rigorous uncertainty quantification (UQ), limiting their usefulness in high-stakes scenarios. We propose conformalized SNN (CF-SNN), a framework that, given a simplicial-complex entity with m prediction targets, generates prediction sets for all m targets simultaneously. Under mild assumptions, CF-SNN guarantees that, for each target, the prediction set contains the true label with a user-specified nominal coverage probability, and the realized miscoverage proportion across all m targets is guaranteed to remain close to the nominal level with high probability. Extensive experiments across a wide range of SC prediction tasks demonstrate that CF-SNN is a flexible UQ framework that achieves user-specified coverage while producing informative prediction sets of small size.
Abstract:Simplicial neural networks (SNNs) are powerful tools for prediction tasks on higher-order relational datasets stored on simplicial complexes (SCs), a higher-order generalization of graphs. However, SNNs usually lack rigorous uncertainty quantification (UQ), limiting their usefulness in high-stakes scenarios. We propose conformalized SNN (CF-SNN), a framework that, given a simplicial-complex entity with m prediction targets, generates prediction sets for all m targets simultaneously. Under mild assumptions, CF-SNN guarantees that, for each target, the prediction set contains the true label with a user-specified nominal coverage probability, and the realized miscoverage proportion across all m targets is guaranteed to remain close to the nominal level with high probability. Extensive experiments across a wide range of SC prediction tasks demonstrate that CF-SNN is a flexible UQ framework that achieves user-specified coverage while producing informative prediction sets of small size.
Machine Learning (stat.ML); Machine Learning (cs.LG)
arXiv:2610.41166 [stat.ML]
(or arXiv:2610.41166v1 [stat.ML] for this version)
https://doi.org/10.48550/arXiv.2610.41166 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 232 cuvinte
Subiecte conexe
Geometry-Aware Uncertainty Quantification via Conformal Prediction on Manifolds
arXiv · 9 iun. 2026
Conformal Uncertainty Quantification Guarantees for Neural Operators
arXiv · 1 sept. 2026
Stochastic Grouping Conformal Prediction for Effective Subgroup Reliability
arXiv · 10 oct. 2026
Conformalized Quantum DeepONet Ensembles for Scalable Operator Learning with Distribution-Free Uncertainty
arXiv · 17 iun. 2026