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.
arXiv:2610.06974v1 Announce Type: new Abstract: Knowledge graph embedding (KGE) methods represent entities and predicates in continuous vector spaces to infer missing knowledge. Despite strong benchm...
arXiv:2607. 16868v1 Announce Type: new Abstract: Large Language Models (LLMs) often produce confidently stated yet unreliable outputs, posing critical challenges for deployment in safety-sensitive applications.
arXiv:2605. 00600v2 Announce Type: replace-cross Abstract: Deep neural networks achieve impressive results across diverse applications, yet their overconfidence on unseen inputs necessitates reliable epistemic uncertainty modeling.
arXiv:2605.18202v2 Announce Type: replace-cross Abstract: Neuro-Symbolic Concept-based Models (NeSy-CBMs) are a family of architectures that integrate neural networks with symbolic reasoning for enha...
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.
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.
The paper introduces a pairwise difference learning (PDL) approach for classification, where a model predicts the outcome difference between two instances and uses these predictions to classify a query instance by averaging over training examples. It presents a meta‑learning technique tailored to this setting and tackles uncertainty quantification by decomposing total uncertainty into aleatoric and epistemic components, extending these measures to PDL. Extensive empirical studies evaluate both predictive accuracy and the model’s awareness of uncertainty.
arXiv:2606. 08831v1 Announce Type: new Abstract: Large language models (LLMs) increasingly perform multi-step reasoning, where intermediate claims form implicit directed acyclic graphs whose node correctness is structurally conditioned on their ancestors.
The paper investigates how sparsity impacts the expressivity of graph neural networks, focusing on relational and temporal variants. It extends the Strong Expressive Lottery Ticket Hypothesis to multi-relational and temporal domains, proving that sufficiently large RGNNs contain sparse subnetworks that preserve 1‑RWL expressivity and providing a probabilistic bound for random pruning. Experiments validate the theoretical bounds, compare them to empirical results on synthetic data, and explore the relationship between pre‑training expressivity, optimization behavior, and prediction quality on temporal and molecular benchmarks.
arXiv:2602.02427v3 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading ou...
arXiv:2605. 04847v2 Announce Type: replace-cross Abstract: Uncertainty quantification (UQ) in graph neural networks (GNNs) is crucial in high-stakes domains but remains a significant challenge.
arXiv:2606. 09856v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such as mathematics and coding where correctness is verifiable.