Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graph-structured data. However, many real-world systems are dynamic in nature, since the graph and node/edge attributes change over time. In recent years, GNN-based models for temporal graphs have emerged as a promising area of research to extend the capabilities of GNNs. In this work, we provide the first comprehensive overview of the current stateof-the-art of temporal GNN, introducing a rigorous formalization of learning settings and tasks and a novel taxonomy categorizing existing approaches in terms of how the temporal aspect is represented and processed. We conclude the survey with a discussion of the most relevant open challenges for the field, from both research and application perspectives.

Longa, A., Lachi, V., Santin, G., Bianchini, M., Lepri, B., Liò, P., et al. (2023). Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities. TRANSACTIONS ON MACHINE LEARNING RESEARCH.

Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities

V. Lachi;M. Bianchini;F. Scarselli;
2023-01-01

Abstract

Graph Neural Networks (GNNs) have become the leading paradigm for learning on (static) graph-structured data. However, many real-world systems are dynamic in nature, since the graph and node/edge attributes change over time. In recent years, GNN-based models for temporal graphs have emerged as a promising area of research to extend the capabilities of GNNs. In this work, we provide the first comprehensive overview of the current stateof-the-art of temporal GNN, introducing a rigorous formalization of learning settings and tasks and a novel taxonomy categorizing existing approaches in terms of how the temporal aspect is represented and processed. We conclude the survey with a discussion of the most relevant open challenges for the field, from both research and application perspectives.
2023
Longa, A., Lachi, V., Santin, G., Bianchini, M., Lepri, B., Liò, P., et al. (2023). Graph Neural Networks for temporal graphs: State of the art, open challenges, and opportunities. TRANSACTIONS ON MACHINE LEARNING RESEARCH.
File in questo prodotto:
File Dimensione Formato  
1129_graph_neural_networks_for_temp.pdf

accesso aperto

Tipologia: PDF editoriale
Licenza: Creative commons
Dimensione 615.37 kB
Formato Adobe PDF
615.37 kB Adobe PDF Visualizza/Apri

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/11365/1244174