Learning Parametrised Graph Shift Operators - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Learning Parametrised Graph Shift Operators

Résumé

In many domains data is currently represented as graphs and therefore, the graph representation of this data becomes increasingly important in machine learning. Network data is, implicitly or explicitly, always represented using a graph shift operator (GSO) with the most common choices being the adjacency, Laplacian matrices and their normalisations. In this paper, a novel parametrised GSO (PGSO) is proposed, where specific parameter values result in the most commonly used GSOs and message-passing operators in graph neural network (GNN) frameworks. The PGSO is suggested as a replacement of the standard GSOs that are used in state-of-the-art GNN architectures and the optimisation of the PGSO parameters is seamlessly included in the model training. It is proved that the PGSO has real eigenvalues and a set of real eigenvectors independent of the parameter values and spectral bounds on the PGSO are derived. PGSO parameters are shown to adapt to the sparsity of the graph structure in a study on stochastic blockmodel networks, where they are found to automatically replicate the GSO regularisation found in the literature. On several real-world datasets the accuracy of state-of-the-art GNN architectures is improved by the inclusion of the PGSO in both node- and graph-classification tasks.
Fichier principal
Vignette du fichier
PGSO_ICLR_2021.pdf (1.19 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04447522 , version 1 (08-02-2024)

Identifiants

Citer

George Dasoulas, Johannes Lutzeyer, Michalis Vazirgiannis. Learning Parametrised Graph Shift Operators. International Conference on Learning Representations (ICLR), May 2021, Online, France. ⟨hal-04447522⟩
1 Consultations
6 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More