Details

Autor(en) / Beteiligte

• Lachaud, Guillaume
• Conde-Cespedes, Patricia
• Trocan, Maria

Titel

Graph Neural Networks-Based Multilabel Classification of Citation Network

Ist Teil von

• Intelligent Information and Database Systems, p.128-140

Ort / Verlag

Cham: Springer Nature Switzerland

Link zum Volltext

Quelle

Alma/SFX Local Collection

Beschreibungen/Notizen

• There is an increasing number of applications where data can be represented as graphs. Besides, it is well-known that artificial intelligence approaches have become a very active and promising research field, mostly due to deep learning technologies. However popular deep learning architectures were designed to treat mostly image and text data. Graph Neural Network is the branch of machine learning which builds neural networks for graph data. In this context, many authors have recently proposed to adapt existing approaches to graphs and networks. In this paper we train three models of Graph Neural Networks on an academic citation network of Computer Science papers, and we explore the advantages of turning the problem into a multilabel classification problem.