Stability of graph convolutional neural networks to stochastic perturbations

Zhan Gao, Elvin Isufi, Alejandro Ribeiro

Research output: Contribution to journalArticleScientificpeer-review

15 Citations (Scopus)


Graph convolutional neural networks (GCNNs) are nonlinear processing tools to learn representations from network data. A key property of GCNNs is their stability to graph perturbations. Current analysis considers deterministic perturbations but fails to provide relevant insights when topological changes are random. This paper investigates the stability of GCNNs to stochastic graph perturbations induced by link losses. In particular, it proves the expected output difference between the GCNN over random perturbed graphs and the GCNN over the nominal graph is upper bounded by a factor that is linear in the link loss probability. We perform the stability analysis in the graph spectral domain such that the result holds uniformly for any graph. This result also shows the role of the nonlinearity and the architecture width and depth, and allows identifying handle to improve the GCNN robustness. Numerical simulations on source localization and robot swarm control corroborate our theoretical findings.
Original languageEnglish
Article number108216
Number of pages15
JournalSignal Processing
Publication statusPublished - 2021


  • Graph convolutional neural networks
  • Graph filters
  • Stability property
  • Stochastic perturbations


Dive into the research topics of 'Stability of graph convolutional neural networks to stochastic perturbations'. Together they form a unique fingerprint.

Cite this