Robust node embedding against graph structural perturbations

DOI10.1016/J.INS.2021.02.046MaRDI QIDQ6086304zbMATH OpenOpenAlexFDO

Authors

Publication date 9 November 2023

Published in Information Sciences (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.ins.2021.02.046

zbMATH Keywords

adversarial attacksdefense methodgraph neural networks

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05)

Recommendations

• Parameter discrepancy hypothesis: adversarial attack for graph data
• Adversarial attacks on graph-level embedding methods: a case study
• Scalable attack on graph data by injecting vicious nodes
• Locality preserving dense graph convolutional networks with graph context-aware node representations
• Multi-graph fusion graph convolutional networks with pseudo-label supervision

Cites work

• An Introduction to Variational Autoencoders
• HesGCN: Hessian graph convolutional networks for semi-supervised classification
• scientific article; zbMATH DE number 1149166 (Why is no real title available?)

Cited in

(4)

• Parameter discrepancy hypothesis: adversarial attack for graph data
• Adversarial attacks on graph-level embedding methods: a case study
• The identical distribution hypothesis is equivalent to the parameter discrepancy hypothesis: adversarial attacks on graph neural networks
• Whole-graph embedding and adversarial attacks for life sciences

This page was built for publication: Robust node embedding against graph structural perturbations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6086304)