Effective long-range propagation remains a central challenge in graph neural networks, as increasing a model's propagation depth does not guarantee that distant nodes effectively influence each other. Sheaf neural networks enrich graph propagation through matrix-valued transport between stalks; still, this expressivity...
J. van Looy, Alessandro Trenta, Alessio Gravina et al.· arXiv (Cornell University)· 2 citations
Graph generative models increasingly rely on Graph Transformers (GT) to capture complex dependencies among nodes and edges. While deeper architectures should provide greater expressive capacity and a broader receptive field, their effectiveness can decline with depth: repeated self-attention progressively contracts nod...
Luca Miglior, Alessio Gravina, D. Bacciu· arXiv.org· 0 citations
We study the problem of recovering the governing ODE of a dynamical system from unstructured, high-dimensional observations such as images. Existing methods for ODE discovery typically assume direct measurements of the variables, or do not provide theoretical guarantees on the learned variables and equations. While Cau...
Alessandro Trenta, Riccardo Massidda, D. Bacciu et al.· 0 citations
It is suggested that likelihood preferences over controlled declarative alternatives and task-conditioned answer selection probe distinct aspects of model behavior, and should not be treated as interchangeable.
Alessandro Bondielli, Lucia C. Passaro, D. Bacciu et al.· arXiv.org· 0 citations
A hybrid deep learning framework for learned one-step tracklet filtering of radar measurements that achieves lower filtering error and improved robustness under severe non-Gaussian disturbances, compared with EKF- and UKF-based analytical baselines.
A. Cabras, Niccolò Pilloni, Victor Mustieles-Pérez et al.· AI Sensors· 0 citations
This work proposes Z-PEFT, a lightweight meta-classifier that relies exclusively on layer-wise spectral measures for classification, and achieves the best performance while maintaining low and scalable computational cost among weight-space detectors.
Nicola Pitzalis, Donald Shenaj, Giacomo Cignoni et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.