Improving Graph Variational Autoencoders with Multi-Hop Simple Convolutions

Erik Jhones F. do Nascimento, Amauri H. Souza, Diego Mesquita

Tutkimustuotos: Artikkeli kirjassa/konferenssijulkaisussaConference article in proceedingsScientificvertaisarvioitu

1 Sitaatiot (Scopus)

Abstrakti

Variational auto-encoding architectures represent one of the most popular approaches to graph generative modeling. These models comprise encoder and a decoder networks, which map back and forth between the input and latent spaces. Notably, most of the literature in variational autoencoders (VAEs) for graphs focuses on developing more efficient architectures at the expense of increased complexity. In this work, we pursue an orthogonal direction and leverage multi-hop linear graph convolutional layers to create efficient yet simple encoders, boosting the performance of graph autoencoders. Our results demonstrate that our approach outperforms popular graph VAE baselines in link prediction tasks.

AlkuperäiskieliEnglanti
OtsikkoESANN 2021 Proceedings - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
Kustantajai6doc.com
Sivut105-110
Sivumäärä6
ISBN (elektroninen)9782875870827
DOI - pysyväislinkit
TilaJulkaistu - 2021
OKM-julkaisutyyppiA4 Artikkeli konferenssijulkaisussa
TapahtumaEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning - Virtual, Online, Bruges, Belgia
Kesto: 6 lokak. 20218 lokak. 2021
Konferenssinumero: 29

Julkaisusarja

NimiESANN 2021 Proceedings - 29th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning

Conference

ConferenceEuropean Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning
LyhennettäESANN
Maa/AlueBelgia
KaupunkiBruges
Ajanjakso06/10/202108/10/2021

Sormenjälki

Sukella tutkimusaiheisiin 'Improving Graph Variational Autoencoders with Multi-Hop Simple Convolutions'. Ne muodostavat yhdessä ainutlaatuisen sormenjäljen.

Siteeraa tätä