Graph Neural Networks (GNNs) are specialized machine learning models designed for analyzing and making predictions based on graph-structured data. In this paper, we introduce a GNN-based approach for the analysis of heterogeneous event graphs. By heterogeneous event graph, we refer to a temporal graph where multiple types of nodes representing events as well as multiple type of edges among events are defined. A distinguishing aspect of the proposed approach lies in the specification of the subgraph of nodes for each event to classify, and in the use of embedding techniques for representing all the relevant features/attributes of the subgraph. The proposed approach is compatible with different GNN models; the use of PSCN, namely a CNN for subgraph classification, is discussed in the paper under two different settings. Preliminary results on two different case-studies, as well as a real application in the field of historical data classification are also discussed.
Using Graph Neural Networks for Heterogeneous Event Classification / V. Bellandi, S. Montanelli, D. Shlyk, S. Siccardi (CEUR WORKSHOP PROCEEDINGS). - In: CEUR Workshop Proceedings / [a cura di] M. Atzori, P. Ciaccia, M. Ceci, F. Mandreoli, D. Malerba, M. Sanguinetti, A. Pellicani, F. Motta. - [s.l] : CEUR, 2024. - pp. 247-259 (( Intervento presentato al 32. convegno SEBD Italian Symposium on Advanced Database Systems : June 23rd to 26th tenutosi a Villasimius nel 2024.
Using Graph Neural Networks for Heterogeneous Event Classification
V. BellandiPrimo
;S. MontanelliSecondo
;D. ShlykPenultimo
;S. SiccardiUltimo
2024
Abstract
Graph Neural Networks (GNNs) are specialized machine learning models designed for analyzing and making predictions based on graph-structured data. In this paper, we introduce a GNN-based approach for the analysis of heterogeneous event graphs. By heterogeneous event graph, we refer to a temporal graph where multiple types of nodes representing events as well as multiple type of edges among events are defined. A distinguishing aspect of the proposed approach lies in the specification of the subgraph of nodes for each event to classify, and in the use of embedding techniques for representing all the relevant features/attributes of the subgraph. The proposed approach is compatible with different GNN models; the use of PSCN, namely a CNN for subgraph classification, is discussed in the paper under two different settings. Preliminary results on two different case-studies, as well as a real application in the field of historical data classification are also discussed.File | Dimensione | Formato | |
---|---|---|---|
paper36.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Dimensione
1.2 MB
Formato
Adobe PDF
|
1.2 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.