Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks

Volume: 35, Issue: 11, Pages: 9524 - 9532
Published: May 18, 2021
Abstract
Graph Neural Networks (GNNs), a generalization of neural networks to graph-structured data, are often implemented using message passes between entities of a graph. While GNNs are effective for node classification, link prediction and graph classification, they are vulnerable to adversarial attacks, i.e., a small perturbation to the structure can lead to a non-trivial performance degradation. In this work, we propose Uncertainty Matching GNN...
Paper Details
Title
Uncertainty-Matching Graph Neural Networks to Defend Against Poisoning Attacks
Published Date
May 18, 2021
Volume
35
Issue
11
Pages
9524 - 9532
Citation AnalysisPro
  • Scinapse’s Top 10 Citation Journals & Affiliations graph reveals the quality and authenticity of citations received by a paper.
  • Discover whether citations have been inflated due to self-citations, or if citations include institutional bias.