1 citations · 2 across the 15 of their papers we have counts for
6 papers · 1 filter
Neural-HSS: Hierarchical Semi-Separable Neural PDE Solver
Pietro Sittoni, Emanuele Zangrando, Angelo A. Casulli +2
Deep learning-based methods have shown remarkable effectiveness in solving PDEs, largely due to their ability to enable fast simulations once trained. However, despite the availabi…
Stuart-Landau Oscillatory Graph Neural Network
Kaicheng Zhang, David N. Reynolds, Piero Deidda +1
Oscillatory Graph Neural Networks (OGNNs) are an emerging class of physics-inspired architectures designed to mitigate oversmoothing and vanishing gradient problems in deep GNNs. I…
Graph-Convolutional-Beta-VAE for Synthetic Abdominal Aorta Aneurysm Generation
Francesco Fabbri, Martino Andrea Scarpolini, Angelo Iollo +2
Synthetic data generation plays a crucial role in medical research by mitigating privacy concerns and enabling large-scale patient data analysis. This study presents a beta-Variati…
Are We Measuring Oversmoothing in Graph Neural Networks Correctly?
Kaicheng Zhang, Piero Deidda, Desmond Higham +1
Oversmoothing is a fundamental challenge in graph neural networks (GNNs): as the number of layers increases, node embeddings become increasingly similar, and model performance drop…
Provable Emergence of Deep Neural Collapse and Low-Rank Bias in -Regularized Nonlinear Networks
Emanuele Zangrando, Piero Deidda, Simone Brugiapaglia +2
We present a unified theoretical framework connecting the first property of Deep Neural Collapse (DNC1) to the emergence of implicit low-rank bias in nonlinear networks trained wit…
Learning the effective order of a hypergraph dynamical system
Leonie Neuhäuser, Michael Scholkemper, Francesco Tudisco +1
Dynamical systems on hypergraphs can display a rich set of behaviours not observable for systems with pairwise interactions. Given a distributed dynamical system with a putative hy…