K-plex cover pooling for graph neural networks - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Article Dans Une Revue Data Mining and Knowledge Discovery Année : 2021

K-plex cover pooling for graph neural networks

Résumé

Graph pooling methods provide mechanisms for structure reduction that are intended to ease the diffusion of context between nodes further in the graph, and that typically leverage community discovery mechanisms or node and edge pruning heuristics. In this paper, we introduce a novel pooling technique which borrows from classical results in graph theory that is non-parametric and generalizes well to graphs of different nature and connectivity patterns. Our pooling method, named KPlexPool, builds on the concepts of graph covers and k-plexes, i.e. pseudo-cliques where each node can miss up to k links. The experimental evaluation on benchmarks on molecular and social graph classification shows that KPlexPool achieves state of the art performances against both parametric and non-parametric pooling methods in the literature, despite generating pooled graphs based solely on topological information.
Fichier principal
Vignette du fichier
2021_Article_.pdf (674.43 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03498374 , version 1 (21-12-2021)

Identifiants

Citer

Davide Bacciu, Alessio Conte, Roberto Grossi, Francesco Landolfi, Andrea Marino. K-plex cover pooling for graph neural networks. Data Mining and Knowledge Discovery, 2021, 35, pp.2200 - 2220. ⟨10.1007/s10618-021-00779-z⟩. ⟨hal-03498374⟩

Collections

INRIA INRIA2
21 Consultations
93 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More