Pooling properties within the Graph Neural network framework - Archive ouverte HAL
Rapport Année : 2023

Pooling properties within the Graph Neural network framework

Propriétés du Pooling dans les réseaux de neurones sur graphes.

Luc Brun
  • Fonction : Auteur
  • PersonId : 837694

Résumé

Graph Neural Networks (GNNs) are inspired from CNNs and aim at transferring the performances observed on images to graphs. In a GNN, convolution and pooling are the main components in the network and these operations are employed in an alternating fashion between each other if a pooling method is used. However, this simple definition of GNN has some issues and their impacts can lead to low prediction performances. The two main issues are identified as over-squashing and over-smoothing. Recent works on these issues only focuses on the graph convolution operator, neglecting the role of pooling operator. This paper aims to investigate the impact of pooling on over-squashing and over-smoothing. Our findings demonstrate that, under certain properties, pooling can reduced over-squashing and prevent over-smoothing. The conditions imposed on pooling to achieve these results are not so restrictive and encompass the majority of methods such as Top-k methods, EdgePool or MIS strategies. Finally, we empirically validate our results.
Fichier principal
Vignette du fichier
smoothing_squashing.pdf (387.52 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04379337 , version 1 (08-01-2024)

Licence

Identifiants

  • HAL Id : hal-04379337 , version 1

Citer

Luc Brun. Pooling properties within the Graph Neural network framework. Image - Laboratoire GREYC - UMR6072. 2023. ⟨hal-04379337⟩
47 Consultations
80 Téléchargements

Partager

More