On the Stability of Gated Graph Neural Networks - Archive ouverte HAL
Pré-Publication, Document De Travail Année : 2023

On the Stability of Gated Graph Neural Networks

Résumé

In this paper, we aim to find the conditions for input-state stability (ISS) and incremental input-state stability (δISS) of Gated Graph Neural Networks (GGNNs). We show that this recurrent version of Graph Neural Networks (GNNs) can be expressed as a dynamical distributed system and, as a consequence, can be analysed using model-based techniques to assess its stability and robustness properties. Then, the stability criteria found can be exploited as constraints during the training process to enforce the internal stability of the neural network. Two distributed control examples, flocking and multi-robot motion control, show that using these conditions increases the performance and robustness of the gated GNNs.
Fichier principal
Vignette du fichier
stability_Graph_Gated_Neural_Networks-1.pdf (1.1 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04110671 , version 1 (30-05-2023)
hal-04110671 , version 2 (21-08-2023)
hal-04110671 , version 3 (24-01-2024)

Licence

Identifiants

Citer

Antonio Marino, Claudio Pacchierotti, Paolo Robuffo Giordano. On the Stability of Gated Graph Neural Networks. 2023. ⟨hal-04110671v1⟩
135 Consultations
213 Téléchargements

Altmetric

Partager

More