Tipo di tesi
Tesi di laurea magistrale
Titolo
Capturing spatiotemporal long-range dependencies in
dynamic graphs
Corso di studi
INFORMATICA
Parole chiave
- dynamic graph
- graph neural networks
- machine learning
- neural networks
- neuralODE
Data inizio appello
11/10/2024
Riassunto (Italiano)
In this thesis, models to address the problem of long-range spatiotemporal dependencies in dynamic graphs are presented and tested on both real and synthetic datasets. These models are obtained through a combination of Graph Neural Networks with the NeuralODE paradigm, exploiting theoretical properties of the dynamical system that arise from the ODE describing the model to guarantee stability during training and more efficient propagation of information both in the spatial dimension (between different nodes of the graph) and the temporal dimension (different timestep of the dynamical graph).
