The problem of multi-task regression over graph nodes has been recently approached through Graph-Instructed Neural Network (GINN), which is a promising architecture belonging to the subset of message-passing graph neural networks. In this work, we discuss the limitations of the Graph-Instructed (GI) layer, and we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages of the EWGI layer and we provide numerical evidence that EWGINNs perform better than GINNs over some graph-structured input data, like the ones inferred from the Barabási-Albert graph, and improve the training regularization on graphs with chaotic connectivity, like the ones inferred from the Erdos–Rényi graph.

Edge-Wise Graph-Instructed Neural Networks / Della Santa, Francesco; Mastropietro, Antonio; Pieraccini, Sandra; Vaccarino, Francesco. - In: JOURNAL OF COMPUTATIONAL SCIENCE. - ISSN 1877-7503. - 85:(2025), pp. 1-6. [10.1016/j.jocs.2024.102518]

Edge-Wise Graph-Instructed Neural Networks

Della Santa, Francesco;Mastropietro, Antonio;Pieraccini, Sandra;Vaccarino, Francesco
2025

Abstract

The problem of multi-task regression over graph nodes has been recently approached through Graph-Instructed Neural Network (GINN), which is a promising architecture belonging to the subset of message-passing graph neural networks. In this work, we discuss the limitations of the Graph-Instructed (GI) layer, and we formalize a novel edge-wise GI (EWGI) layer. We discuss the advantages of the EWGI layer and we provide numerical evidence that EWGINNs perform better than GINNs over some graph-structured input data, like the ones inferred from the Barabási-Albert graph, and improve the training regularization on graphs with chaotic connectivity, like the ones inferred from the Erdos–Rényi graph.
File in questo prodotto:
File Dimensione Formato  
1-s2.0-S1877750324003119-main.pdf

accesso aperto

Tipologia: 2a Post-print versione editoriale / Version of Record
Licenza: Creative commons
Dimensione 1.44 MB
Formato Adobe PDF
1.44 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/11583/2996523