Low-Rank Projections of GCNs Laplacian
Type de document :
Autre communication scientifique (congrès sans actes - poster - séminaire...): Communication dans un congrès avec actes
URL permanente :
Titre :
Low-Rank Projections of GCNs Laplacian
Auteur(s) :
Grinsztajn, Nathan [Auteur]
Scool [Scool]
Preux, Philippe [Auteur]
Scool [Scool]
Oyallon, Edouard [Auteur]
Machine Learning and Information Access [MLIA]
Scool [Scool]
Preux, Philippe [Auteur]
Scool [Scool]
Oyallon, Edouard [Auteur]
Machine Learning and Information Access [MLIA]
Titre de la manifestation scientifique :
ICLR 2021 Workshop GTRL
Ville :
Online
Pays :
France
Date de début de la manifestation scientifique :
2021-05-07
Discipline(s) HAL :
Informatique [cs]/Apprentissage [cs.LG]
Informatique [cs]/Intelligence artificielle [cs.AI]
Informatique [cs]/Intelligence artificielle [cs.AI]
Résumé en anglais : [en]
In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation experiments, we evaluate the impact of bandpass filtering on the performance of a GCN: ...
Lire la suite >In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation experiments, we evaluate the impact of bandpass filtering on the performance of a GCN: we empirically show that most of the necessary and used information for nodes classification is contained in the low-frequency domain, and thus contrary to images, high frequencies are less crucial to community detection. In particular, it is sometimes possible to obtain accuracies at a state-of-the-art level with simple classifiers that rely only on a few low frequencies.Lire moins >
Lire la suite >In this work, we study the behavior of standard models for community detection under spectral manipulations. Through various ablation experiments, we evaluate the impact of bandpass filtering on the performance of a GCN: we empirically show that most of the necessary and used information for nodes classification is contained in the low-frequency domain, and thus contrary to images, high frequencies are less crucial to community detection. In particular, it is sometimes possible to obtain accuracies at a state-of-the-art level with simple classifiers that rely only on a few low frequencies.Lire moins >
Langue :
Anglais
Comité de lecture :
Non
Audience :
Internationale
Vulgarisation :
Non
Collections :
Source :
Date de dépôt :
2021-11-13T02:30:41Z
Fichiers
- https://hal.archives-ouvertes.fr/hal-03248056/document
- Accès libre
- Accéder au document
- http://arxiv.org/pdf/2106.07360
- Accès libre
- Accéder au document