Alessio Gravina

Oscillatory Neural Dynamics over Sheaves

Jan-Willem Van Looy, Alessandro Trenta, Alessio Gravina +5

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 i…

Let the Heads Talk: Beyond Diagonal Graph Attention

Riccardo Ali, Alessio Borgi, Mario Severino +4

Sheaf Neural Networks generalize scalar-weighted message passing by replacing scalar edge weights with linear transport maps between local feature spaces. Yet the role of this matr…

Stable Transformers for Graph Generation

Luca Miglior, Alessio Gravina, Davide Bacciu

Graph generative models increasingly rely on Graph Transformers (GT) to capture complex dependencies among nodes and edges. While deeper architectures should provide greater expres…

Graph Hierarchical Recurrence for Long-Range Generalization

Stefano Carotti, Marco Pacini, Alessio Gravina +3

Graph Neural Networks and Graph Transformers have become central to graph learning, combining expressive representation learning with sample-efficient inductive biases. Yet they re…

Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation

Luca Miglior, Matteo Tolloso, Alessio Gravina +1

Effectively capturing long-range interactions remains a fundamental yet unresolved challenge in graph neural network (GNN) research, critical for applications across diverse fields…

Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics

Tai Hoang, Alessandro Trenta, Alessio Gravina +4

Learning to simulate complex physical systems from data has emerged as a promising way to overcome the limitations of traditional numerical solvers, which often require prohibitive…

Return of ChebNet: Understanding and Improving an Overlooked GNN on Long Range Tasks

Ali Hariri, Álvaro Arroyo, Alessio Gravina +6

ChebNet, one of the earliest spectral GNNs, has largely been overshadowed by Message Passing Neural Networks (MPNNs), which gained popularity for their simplicity and effectiveness…

Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling

Andrea Ceni, Alessio Gravina, Claudio Gallicchio +3

The recent success of State-Space Models (SSMs) in sequence modeling has motivated their adaptation to graph learning, giving rise to Graph State-Space Models (GSSMs). However, exi…

On Vanishing Gradients, Over-Smoothing, and Over-Squashing in GNNs: Bridging Recurrent and Graph Learning

Álvaro Arroyo, Alessio Gravina, Benjamin Gutteridge +5

Graph Neural Networks (GNNs) are models that leverage the graph structure to transmit information between nodes, typically through the message-passing operation. While widely succe…

GRAMA: Adaptive Graph Autoregressive Moving Average Models

Moshe Eliasof, Alessio Gravina, Andrea Ceni +3

Graph State Space Models (SSMs) have recently been introduced to enhance Graph Neural Networks (GNNs) in modeling long-range interactions. Despite their success, existing methods e…

Information propagation dynamics in Deep Graph Networks

Alessio Gravina

Graphs are a highly expressive abstraction for modeling entities and their relations, such as molecular structures, social networks, and traffic networks. Deep Graph Networks (DGNs…

Long Range Propagation on Continuous-Time Dynamic Graphs

Alessio Gravina, Giulio Lovisotto, Claudio Gallicchio +2

Learning Continuous-Time Dynamic Graphs (C-TDGs) requires accurately modeling spatio-temporal information on streams of irregularly sampled events. While many methods have been pro…

Port-Hamiltonian Architectural Bias for Long-Range Propagation in Deep Graph Networks

Simon Heilig, Alessio Gravina, Alessandro Trenta +2

The dynamics of information diffusion within graphs is a critical open issue that heavily influences graph representation learning, especially when considering long-range propagati…