MRMP: Multi-Rate Magnitude Pruning of Graph Convolutional Networks - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

MRMP: Multi-Rate Magnitude Pruning of Graph Convolutional Networks

Hichem Sahbi

Résumé

In this paper, we devise a novel lightweight Graph Convolutional Network (GCN) design dubbed as Multi-Rate Magnitude Pruning (MRMP) that jointly trains network topology and weights. Our method is variational and proceeds by aligning the weight distribution of the learned networks with an a priori distribution. In the one hand, this allows implementing any fixed pruning rate, and also enhancing the generalization performances of the designed lightweight GCNs. In the other hand, MRMP achieves a joint training of multiple GCNs, on top of shared weights, in order to extrapolate accurate networks at any targeted pruning rate without retraining their weights. Extensive experiments conducted on the challenging task of skeleton-based recognition show a substantial gain of our lightweight GCNs particularly at very high pruning regimes.
Fichier principal
Vignette du fichier
31_mrmp_multi_rate_magnitude_prun.pdf (533.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04274267 , version 1 (07-11-2023)

Identifiants

  • HAL Id : hal-04274267 , version 1

Citer

Hichem Sahbi. MRMP: Multi-Rate Magnitude Pruning of Graph Convolutional Networks. ES-FoMo Workshop at the International Conference on Machine Learning – ICML 2023, Jul 2023, Honululu, United States. ⟨hal-04274267⟩
115 Consultations
29 Téléchargements

Partager

Gmail Facebook X LinkedIn More