Link prediction aims to reveal missing edges in a graph. We introduce a deep graph convolutional Gaussian process model for this task, which addresses recent challenges in graph machine learning with oversmoothing and overfitting. Using simplified graph convolutions, we transform a Gaussian process to leverage the topological information of the graph domain. To scale the Gaussian process model to larger graphs, we introduce a variational inducing point method that places pseudo-inputs on a graph-structured domain. Multiple Gaussian processes are assembled into a hierarchy whose structure allows skipping convolutions and thus counteracting oversmoothing. The proposed model represents the first Gaussian process for link prediction that makes use of both node features and topological information. We evaluate our model on multiple graph data sets with up to thousands of nodes and report consistent improvements over competitive link prediction approaches.
Bayesian Link Prediction with Deep Graph Convolutional Gaussian Processes / Opolka, F. L.; Lio, P.. - 151:(2022), pp. 4835-4852. (Intervento presentato al convegno International Conference on Artificial Intelligence and Statistics tenutosi a Virtual, Online).
Bayesian Link Prediction with Deep Graph Convolutional Gaussian Processes
Lio P.
2022
Abstract
Link prediction aims to reveal missing edges in a graph. We introduce a deep graph convolutional Gaussian process model for this task, which addresses recent challenges in graph machine learning with oversmoothing and overfitting. Using simplified graph convolutions, we transform a Gaussian process to leverage the topological information of the graph domain. To scale the Gaussian process model to larger graphs, we introduce a variational inducing point method that places pseudo-inputs on a graph-structured domain. Multiple Gaussian processes are assembled into a hierarchy whose structure allows skipping convolutions and thus counteracting oversmoothing. The proposed model represents the first Gaussian process for link prediction that makes use of both node features and topological information. We evaluate our model on multiple graph data sets with up to thousands of nodes and report consistent improvements over competitive link prediction approaches.File | Dimensione | Formato | |
---|---|---|---|
Opolka_Bayesian_2022.pdf
solo gestori archivio
Tipologia:
Versione editoriale (versione pubblicata con il layout dell'editore)
Licenza:
Tutti i diritti riservati (All rights reserved)
Dimensione
419.49 kB
Formato
Adobe PDF
|
419.49 kB | Adobe PDF | Contatta l'autore |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.