AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Measuring the Privacy Leakage via Graph Reconstruction Attacks on Simplicial Neural Networks (Student Abstract)

Huixin Zhan, Kun Zhang, Keyi Lu, Victor S. Sheng

AAAI 2023 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation learning · 2 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use SNN rather than GCN representations for the reconstruction attackGRA · CiteSeerAUC: 0.8832 -> 0.9833Improved
Use SNN rather than GCN representations for the reconstruction attackGRA · CoraAUC: 0.8900 -> 0.9713Improved
Use SNN rather than GCN representations for the reconstruction attackGRA · PubmedAUC: 0.8937 -> 0.9826Improved
Use SNN rather than GCN representations for the reconstruction attackGRA · ComputersAUC: 0.9041 -> 0.9802Improved
Use SNN rather than GCN representations for the reconstruction attackGRA · PhotosAUC: 0.9157 -> 0.9832Improved
Use SNN rather than GAT representations for the reconstruction attackGRA · CiteSeerAUC: 0.9224 -> 0.9833Improved
Use SNN rather than GAT representations for the reconstruction attackGRA · CoraAUC: 0.9640 -> 0.9713Improved
Use SNN rather than GAT representations for the reconstruction attackGRA · PubmedAUC: 0.9704 -> 0.9826Improved
Use SNN rather than GAT representations for the reconstruction attackGRA · ComputersAUC: 0.9800 -> 0.9802Improved
Use SNN rather than GAT representations for the reconstruction attackGRA · PhotosAUC: 0.9703 -> 0.9832Improved
Use GAT rather than GCN representations for the reconstruction attackGRA · CiteSeerAUC: 0.8832 -> 0.9224Improved
Use GAT rather than GCN representations for the reconstruction attackGRA · CoraAUC: 0.8900 -> 0.9640Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy