TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems

• URL: http://arxiv.org/abs/2606.26664v1
• Date: Thu, 25 Jun 2026 06:55:06 GMT
• Title: TGHE: Template-based Graph Homomorphic Encryption for Privacy-Preserving GNN Inference in Edge-Cloud Systems
• Abstract summary: Existing homomorphic encryption (HE)-based GNN systems adopt a graphcentric paradigm that couples per-query cost to global graph size.<n>We propose TGHE, an ego-centric framework that resolves this by exploiting a template phenomenon: local trees in transaction graphs converge into a small set of structural shapes.<n> TGHE canonicalizes ego-graphs at the edge and packs structurally identical trees into shared ciphertexts for SIMD-parallel encrypted inference.
• Score: 1.9552564628602804
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• CoRe-GNN: Multilevel Message passing on Coarsened graphs [13.325673513204377]
  Training Graph Neural Networks on large graphs is challenged by the memory cost of node representations across layers.<n>We show that several existing scalable approaches can be written as structured modifications of the GNN propagation matrix.<n>In particular, graph coarsening replaces it by a lowrank approximation that enables spectral guarantees but assigns uniform representations to nodes.
  arXiv  Detail & Related papers  (2026-08-03T12:18:58Z)
• AdaGraph: A Graph-Native Clustering Algorithm That Overcomes the Curse of Dimensionality and Enables Scientific Discovery [0.0]
  We present AdaGraph, a graph-native clustering algorithm born from the Structure-Centric Machine Learning (SC-ML) paradigm.<n>AdaGraph operates entirely within the kNN graph topology.<n>It pairs with Graph-SCOPE, the topology-based cluster validity index introduced as a separate SC-ML contribution.
  arXiv  Detail & Related papers  (2026-05-05T01:42:59Z)
• GraphTreeGen: Subtree-Centric Approach to Efficient and Supervised Graph Generation [6.138671548064356]
  GraphTreeGen (GTG) is a subtree-centric generative framework for efficient, accurate connectome synthesis.<n>GTG decomposes each connectome into entropy-guided k-hop trees capturing informative local structure.<n>Its modular design enables extensions to connectome super-resolution and cross-modality synthesis.
  arXiv  Detail & Related papers  (2025-08-13T11:02:38Z)
• Scalable Graph Generative Modeling via Substructure Sequences [50.32639806800683]
  We introduce Generative Graph Pattern Machine (G$2$PM), a generative Transformer pre-training framework for graphs.<n>G$2$PM represents graph instances (nodes, edges, or entire graphs) as sequences of substructures.<n>It employs generative pre-training over the sequences to learn generalizable and transferable representations.
  arXiv  Detail & Related papers  (2025-05-22T02:16:34Z)
• Disentangled Condensation for Large-scale Graphs [29.384060761810172]
  Graph condensation has emerged as an intriguing technique to save the expensive training costs of Graph Neural Networks (GNNs)<n>We propose to disentangle the condensation process into a two-stage GNN-free paradigm, independently condensing nodes and generating edges.<n>This simple yet effective approach achieves at least 10 times faster than state-of-the-art methods with comparable accuracy on medium-scale graphs.
  arXiv  Detail & Related papers  (2024-01-18T09:59:00Z)
• Graph Transformer GANs with Graph Masked Modeling for Architectural Layout Generation [153.92387500677023]
  We present a novel graph Transformer generative adversarial network (GTGAN) to learn effective graph node relations. The proposed graph Transformer encoder combines graph convolutions and self-attentions in a Transformer to model both local and global interactions. We also propose a novel self-guided pre-training method for graph representation learning.
  arXiv  Detail & Related papers  (2024-01-15T14:36:38Z)
• NodeFormer: A Scalable Graph Structure Learning Transformer for Node Classification [70.51126383984555]
  We introduce a novel all-pair message passing scheme for efficiently propagating node signals between arbitrary nodes. The efficient computation is enabled by a kernerlized Gumbel-Softmax operator. Experiments demonstrate the promising efficacy of the method in various tasks including node classification on graphs.
  arXiv  Detail & Related papers  (2023-06-14T09:21:15Z)
• EGRC-Net: Embedding-induced Graph Refinement Clustering Network [66.44293190793294]
  We propose a novel graph clustering network called Embedding-Induced Graph Refinement Clustering Network (EGRC-Net) EGRC-Net effectively utilizes the learned embedding to adaptively refine the initial graph and enhance the clustering performance. Our proposed methods consistently outperform several state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-11-19T09:08:43Z)
• SCGC : Self-Supervised Contrastive Graph Clustering [1.1470070927586016]
  Graph clustering discovers groups or communities within networks. Deep learning methods such as autoencoders cannot incorporate rich structural information. We propose Self-Supervised Contrastive Graph Clustering (SCGC)
  arXiv  Detail & Related papers  (2022-04-27T01:38:46Z)
• MGAE: Masked Autoencoders for Self-Supervised Learning on Graphs [55.66953093401889]
  Masked graph autoencoder (MGAE) framework to perform effective learning on graph structure data. Taking insights from self-supervised learning, we randomly mask a large proportion of edges and try to reconstruct these missing edges during training.
  arXiv  Detail & Related papers  (2022-01-07T16:48:07Z)
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks [82.31087406264437]
  We present a unified GNN sparsification (UGS) framework that simultaneously prunes the graph adjacency matrix and the model weights. We further generalize the popular lottery ticket hypothesis to GNNs for the first time, by defining a graph lottery ticket (GLT) as a pair of core sub-dataset and sparse sub-network.
  arXiv  Detail & Related papers  (2021-02-12T21:52:43Z)
• Connecting Graph Convolutional Networks and Graph-Regularized PCA [23.592657600394215]
  Graph convolution operator of the GCN model is originally motivated from a localized first-order approximation of spectral graph convolutions. We establish a textitmathematical connection between graph convolution and graph-regularized PCA (GPCA)
  arXiv  Detail & Related papers  (2020-06-22T14:27:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.