用模板化方法加速金融图神经网络的加密推理，支持超大规模动态图。
TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
- 基于局部图结构模板，将同构子图打包加密并行计算。
- 在370万节点图上实现66.9倍加速，准确率损失小于0.002 AUC。
- 适合边缘-云端协同的隐私保护金融图分析场景。
现有的基于同态加密（HE）的图神经网络系统采用图中心范式，查询开销与全局图规模耦合，限制了最大节点数至约2万，难以适应动态的大规模金融图。我们提出TGHE（基于模板的图同态加密），一种以用户为中心的框架，利用交易图中局部计算树趋向于少数结构形态的规律。TGHE在边缘端对根图进行标准化，并将结构相同的子图打包进共享的CKKS密文，实现SIMD并行加密推理，通过近似模板拟合和拓扑坍缩两个长尾优化器确保全范围的SIMD覆盖。在包含370万节点、430万边的DGraphFin数据集上，TGHE-Collapse相比串行加密基线实现66.9倍加速，且准确率损失低于0.002 AUC。
原文摘要 · Abstract (English)
Existing homomorphic encryption (HE)-based GNN systems adopt a graph-centric paradigm that couples per-query cost to global graph size, limiting evaluations to at most ~20k nodes and making them incompatible with dynamic, large-scale financial graphs. We propose TGHE (Template-based Graph Homomorphic Encryption), an ego-centric framework that resolves this by exploiting a template phenomenon: local computation trees in transaction graphs converge into a small set of structural shapes. TGHE canonicalizes ego-graphs at the edge and packs structurally identical trees into shared CKKS ciphertexts for SIMD-parallel encrypted inference, with two long-tail optimizers (Approximate Template Fitting and Topology Collapse) ensuring full SIMD coverage. On DGraphFin (3.7M nodes, 4.3M edges), TGHE-Collapse achieves a 66.9x speedup over the sequential encrypted baseline with less than 0.002 AUC loss.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。