Preprint
Aug 2026
PriDyG: Privacy-preserving Dynamic Graph Inference with LLM-GNN Collaboration
Experiments on four benchmarks for node classification and link prediction show that PriDyG consistently outperforms geometrically decaying baselines under the same privacy budget and matches the utility of naive per-update retraining while reducing cumulative privacy cost by up to three orders of magnitude.
Yuyang Xia, Ruixuan Liu, Li Xiong
· 0 citations