Pooling properties within the Graph Neural network framework
Propriétés du pooling dans le cadre des réseaux de neuronnes sur graphes.
Résumé
Pooling properties within the Graph Neural
network framework
luc Brun
May 2023
Abstract
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 oper-
ator, 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 prop-
erties, pooling can reduced over-squashing and prevent over-smoothing.
The conditions imposed on pooling to achieve these results are not so re-
strictive and encompass the majority of methods such as Top-k methods,
EdgePool or MIS strategies. Finally, we empirically validate our results
Domaines
Intelligence artificielle [cs.AI]Origine | Fichiers produits par l'(les) auteur(s) |
---|---|
licence |