Most Graph Convolutions (GCs) proposed in the Graph Neural Networks (GNNs) literature share the principle of computing topologically enriched node representations based on the ones of their neighbors. In this paper, we propose a novel GNN named Tangent Graph Convolutional Network (TGCN) that, in addition to the traditional GC approach, exploits a novel GC that computes node embeddings based on the differences between the attributes of a vertex and the attributes of its neighbors. This allows the GC to characterize each node's neighbor by computing its tangent space representation with respect to the considered vertex.

Tangent Graph Convolutional Network

luca pasa
;
nicolò navarin;alessandro sperduti
2021

Abstract

Most Graph Convolutions (GCs) proposed in the Graph Neural Networks (GNNs) literature share the principle of computing topologically enriched node representations based on the ones of their neighbors. In this paper, we propose a novel GNN named Tangent Graph Convolutional Network (TGCN) that, in addition to the traditional GC approach, exploits a novel GC that computes node embeddings based on the differences between the attributes of a vertex and the attributes of its neighbors. This allows the GC to characterize each node's neighbor by computing its tangent space representation with respect to the considered vertex.
2021
ESANN 2021 - Proceedings, 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, ESANN 2021
9782875870827
File in questo prodotto:
File Dimensione Formato  
ES2021-143.pdf

accesso aperto

Tipologia: Published (publisher's version)
Licenza: Creative commons
Dimensione 1.54 MB
Formato Adobe PDF
1.54 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/11577/3440158
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 1
  • ???jsp.display-item.citation.isi??? ND
  • OpenAlex ND
social impact