K-plex cover pooling for graph neural networks - Archive ouverte HAL Access content directly
Journal Articles Data Mining and Knowledge Discovery Year : 2021

K-plex cover pooling for graph neural networks

(1) , (1) , (2, 1) , (1) , (3)
1
2
3

Abstract

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
Origin : Publisher files allowed on an open archive

Dates and versions

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

Identifiers

Cite

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
18 View
45 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More