LFGCN: Levitating over Graphs with Levy Flights - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

LFGCN: Levitating over Graphs with Levy Flights

Résumé

Due to high utility in many applications, from social networks to blockchain to power grids, deep learning on non-Euclidean objects such as graphs and manifolds, coined Geometric Deep Learning (GDL), continues to gain an ever increasing interest. We propose a new Lévy Flights Graph Convolutional Networks (LFGCN) method for semi-supervised learning, which casts the Lévy Flights into random walks on graphs and, as a result, allows both to accurately account for the intrinsic graph topology and to substantially improve classification performance, especially for heterogeneous graphs. Furthermore, we propose a new preferential P-DropEdge method based on the Girvan-Newman argument. That is, in contrast to uniform removing of edges as in DropEdge, following the Girvan-Newman algorithm, we detect network periphery structures using information on edge betweenness and then remove edges according to their betweenness centrality. Our experimental results on semi-supervised node classification tasks demonstrate that the LFGCN coupled with P-DropEdge accelerates the training task, increases stability and further improves predictive accuracy of learned graph topology structure. Finally, in our case studies we bring the machinery of LFGCN and other deep networks tools to analysis of power grid networks - the area where the utility of GDL remains untapped.
Fichier principal
Vignette du fichier
ICDM2020paper.pdf (651.97 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03123684 , version 1 (28-01-2021)

Licence

Paternité

Identifiants

Citer

Yuzhou Chen, Yulia R Gel, Konstantin Avrachenkov. LFGCN: Levitating over Graphs with Levy Flights. IEEE ICDM 2020 - International Conference on Data Mining, Nov 2020, Sorrento, Italy. ⟨hal-03123684⟩
48 Consultations
51 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More