Artículo
Deep embeddings and Graph Neural Networks: using context to improve domain-independent predictions
Autor/es | Sola Espinosa, Fernando Luis
![]() ![]() ![]() ![]() ![]() Ayala Hernández, Daniel ![]() ![]() ![]() ![]() ![]() ![]() ![]() Hernández Salmerón, Inmaculada Concepción ![]() ![]() ![]() ![]() ![]() ![]() ![]() Ruiz Cortés, David ![]() ![]() ![]() ![]() ![]() ![]() ![]() |
Departamento | Universidad de Sevilla. Departamento de Lenguajes y Sistemas Informáticos |
Fecha de publicación | 2023-06-28 |
Fecha de depósito | 2023-06-28 |
Publicado en |
|
Resumen | Graph neural networks (GNNs) are deep learning architectures that apply graph convolutions through message-passing processes between nodes, represented as embeddings. GNNs have recently become popular because of their ... Graph neural networks (GNNs) are deep learning architectures that apply graph convolutions through message-passing processes between nodes, represented as embeddings. GNNs have recently become popular because of their ability to obtain a contextual representation of each node taking into account information from its surroundings. However, existing work has focused on the development of GNN architectures, using basic domain-specific information about the nodes to compute embeddings. Meanwhile, in the closely-related area of knowledge graphs, much effort has been put towards developing deep learning techniques to obtain node embeddings that preserve information about relationships and structure without relying on domain-specific data. The potential application of deep embeddings of knowledge graphs in GNNs remains largely unexplored. In this paper, we carry out a number of experiments to answer open research questions about the impact on GNNs performance when combined with deep embeddings. We test 7 different deep embeddings across several attribute prediction tasks in two state-of-art attribute-rich datasets. We conclude that, while there is a significant performance improvement, its magnitude varies heavily depending on the specific task and deep embedding technique considered. |
Agencias financiadoras | Ministerio de Ciencia, Innovación y Universidades (MICINN). España Junta de Andalucía |
Identificador del proyecto | PID2019- 105471RB-I00
![]() P18-RT-1060 ![]() US-1380565 ![]() |
Cita | Sola, F.d., Ayala Hernández, D., Hernández Salmerón, I.C. y Ruiz Cortés, D. (2023). Deep embeddings and Graph Neural Networks: using context to improve domain-independent predictions. Applied Intelligence. https://doi.org/10.1007/s10489-023-04685-3. |
Ficheros | Tamaño | Formato | Ver | Descripción |
---|---|---|---|---|
Deep embeddings.pdf | 1.067Mb | ![]() | Ver/ | |