Node Feature Kernels Increase Graph Convolutional Network Robustness - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Node Feature Kernels Increase Graph Convolutional Network Robustness

Résumé

The robustness of the much-used Graph Convolutional Networks (GCNs) to perturbations of their input is becoming a topic of increasing importance. In this paper, the random GCN is introduced for which a random matrix theory analysis is possible. This analysis suggests that if the graph is sufficiently perturbed, or in the extreme case random, then the GCN fails to benefit from the node features. It is furthermore observed that enhancing the message passing step in GCNs by adding the node feature kernel to the adjacency matrix of the graph structure solves this problem. An empirical study of a GCN utilised for node classification on six real datasets further confirms the theoretical findings and demonstrates that perturbations of the graph structure can result in GCNs performing significantly worse than Multi-Layer Perceptrons run on the node features alone. In practice, adding a node feature kernel to the message passing of perturbed graphs results in a significant improvement of the GCN's performance, thereby rendering it more robust to graph perturbations. Our code is publicly available at:https://github.com/ChangminWu/RobustGCN.
Fichier principal
Vignette du fichier
1070.pdf (844.9 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04447471 , version 1 (08-02-2024)

Identifiants

Citer

Mohamed El Amine Seddik, Changmin Wu, Johannes Lutzeyer, Michalis Vazirgiannis. Node Feature Kernels Increase Graph Convolutional Network Robustness. International Conference on Artificial Intelligence and Statistics (AISTATS), Mar 2022, Online, France. ⟨hal-04447471⟩
3 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More