Distributed-order fractional graph operating network

K Zhao, X Li, Q Kang, F Ji, Q Ding… - Advances in …, 2025‏ - proceedings.neurips.cc
We introduce the Distributed-order fRActional Graph Operating Network (DRAGON), a novel
continuous Graph Neural Network (GNN) framework that incorporates distributed-order …

Temporal graph odes for irregularly-sampled time series

A Gravina, D Zambon, D Bacciu, C Alippi - arxiv preprint arxiv:2404.19508, 2024‏ - arxiv.org
Modern graph representation learning works mostly under the assumption of dealing with
regularly sampled temporal graph snapshots, which is far from realistic, eg, social networks …

Information propagation dynamics in Deep Graph Networks

A Gravina - arxiv preprint arxiv:2410.10464, 2024‏ - arxiv.org
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) …

GRAMA: Adaptive Graph Autoregressive Moving Average Models

M Eliasof, A Gravina, A Ceni, C Gallicchio… - arxiv preprint arxiv …, 2025‏ - arxiv.org
Graph State Space Models (SSMs) have recently been introduced to enhance Graph Neural
Networks (GNNs) in modeling long-range interactions. Despite their success, existing …

Resilient Graph Neural Networks: A Coupled Dynamical Systems Approach

M Eliasof, D Murari, F Sherry, CB Schönlieb - ECAI 2024, 2024‏ - ebooks.iospress.nl
Abstract Graph Neural Networks (GNNs) have established themselves as a key component
in addressing diverse graph-based tasks. Despite their notable successes, GNNs remain …

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

S Heilig, A Gravina, A Trenta, C Gallicchio… - … Conference on Learning …‏ - openreview.net
The dynamics of information diffusion within graphs is a critical open issue that heavily
influences graph representation learning, especially when considering long-range …