The paper introduces GraphPub, a novel framework for protecting graph topology while ensuring data availability. By utilizing reverse learning and encoder-decoder mechanisms, false edges are introduced to replace real edges, maintaining model accuracy close to the original graph. Experimental results demonstrate the effectiveness of GraphPub in preserving privacy while maintaining high model accuracy under stringent privacy budgets. The study also explores degree preservation and scalability across different GNN models.
Key Points:
To Another Language
from source content
arxiv.org
Key Insights Distilled From
by Wanghan Xu,B... at arxiv.org 03-04-2024
https://arxiv.org/pdf/2403.00030.pdfDeeper Inquiries