EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy
Graph Neural Networks (GNNs) have shown considerable success in learning from graph-structured data, but their use in privacy-sensitive areas remains difficult because graph structure can leak sensitive link information. To satisfy edge-level differential privacy, a common approach is to inject noise into all elements of the graph's adjacency matrix, thereby obfuscating the existence of any single edge. However, stronger privacy requires more noise, and excessive noise reduces utility, making the privacy-utility balance a major barrier to practical privacy-preserving graph learning. To addre
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- LinkedLinked via arxiv author · 85%Wenxiu Ding →
“EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy”
- LinkedLinked via arxiv author · 85%Muzhi Liu →
“EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy”
- LinkedLinked via arxiv author · 85%Zizheng Yan →
“EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy”
- LinkedLinked via arxiv author · 85%Mingjun Wang →
“EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy”
- LinkedLinked via arxiv author · 85%Yifan Zhao →
“EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy”
- LinkedLinked via arxiv author · 85%Qiao Liu →
“EdgeRefine: Privacy-Utility Balance for Graphs via Jaccard Sampling under Edge Differential Privacy”
- PossiblePossibly related (embedding) · 60%meta-pytorch/opacus →