FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks

Zhaoxuan Kan, Husheng Han, Shangyi Shi, Tenghui Hua, Hang Lu, Xiaowei Li, Jianan Mu, Xing Hu
Proceedings of the 42nd International Conference on Machine Learning, PMLR 267:28832-28848, 2025.

Abstract

Graph Convolutional Neural Networks (GCNs) have gained widespread popularity in various fields like personal healthcare and financial systems, due to their remarkable performance. Despite the growing demand for cloud-based GCN services, privacy concerns over sensitive graph data remain significant. Homomorphic Encryption (HE) facilitates Privacy-Preserving Machine Learning (PPML) by allowing computations to be performed on encrypted data. However, HE introduces substantial computational overhead, particularly for GCN operations that require rotations and multiplications in matrix products. The sparsity of GCNs offers significant performance potential, but their irregularity introduces additional operations that reduce practical gains. In this paper, we propose FicGCN, a HE-based framework specifically designed to harness the sparse characteristics of GCNs and strike a globally optimal balance between aggregation and combination operations. FicGCN employs a latency-aware packing scheme, a Sparse Intra-Ciphertext Aggregation (SpIntra-CA) method to minimize rotation overhead, and a region-based data reordering driven by local adjacency structure. We evaluated FicGCN on several popular datasets, and the results show that FicGCN achieved the best performance across all tested datasets, with up to a $4.10\times$ improvement over the latest design.

Cite this Paper

BibTeX
@InProceedings{pmlr-v267-kan25a, title = {{F}ic{GCN}: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks}, author = {Kan, Zhaoxuan and Han, Husheng and Shi, Shangyi and Hua, Tenghui and Lu, Hang and Li, Xiaowei and Mu, Jianan and Hu, Xing}, booktitle = {Proceedings of the 42nd International Conference on Machine Learning}, pages = {28832--28848}, year = {2025}, editor = {Singh, Aarti and Fazel, Maryam and Hsu, Daniel and Lacoste-Julien, Simon and Berkenkamp, Felix and Maharaj, Tegan and Wagstaff, Kiri and Zhu, Jerry}, volume = {267}, series = {Proceedings of Machine Learning Research}, month = {13--19 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v267/main/assets/kan25a/kan25a.pdf}, url = {https://proceedings.mlr.press/v267/kan25a.html}, abstract = {Graph Convolutional Neural Networks (GCNs) have gained widespread popularity in various fields like personal healthcare and financial systems, due to their remarkable performance. Despite the growing demand for cloud-based GCN services, privacy concerns over sensitive graph data remain significant. Homomorphic Encryption (HE) facilitates Privacy-Preserving Machine Learning (PPML) by allowing computations to be performed on encrypted data. However, HE introduces substantial computational overhead, particularly for GCN operations that require rotations and multiplications in matrix products. The sparsity of GCNs offers significant performance potential, but their irregularity introduces additional operations that reduce practical gains. In this paper, we propose FicGCN, a HE-based framework specifically designed to harness the sparse characteristics of GCNs and strike a globally optimal balance between aggregation and combination operations. FicGCN employs a latency-aware packing scheme, a Sparse Intra-Ciphertext Aggregation (SpIntra-CA) method to minimize rotation overhead, and a region-based data reordering driven by local adjacency structure. We evaluated FicGCN on several popular datasets, and the results show that FicGCN achieved the best performance across all tested datasets, with up to a $4.10\times$ improvement over the latest design.} }
Endnote
%0 Conference Paper %T FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks %A Zhaoxuan Kan %A Husheng Han %A Shangyi Shi %A Tenghui Hua %A Hang Lu %A Xiaowei Li %A Jianan Mu %A Xing Hu %B Proceedings of the 42nd International Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2025 %E Aarti Singh %E Maryam Fazel %E Daniel Hsu %E Simon Lacoste-Julien %E Felix Berkenkamp %E Tegan Maharaj %E Kiri Wagstaff %E Jerry Zhu %F pmlr-v267-kan25a %I PMLR %P 28832--28848 %U https://proceedings.mlr.press/v267/kan25a.html %V 267 %X Graph Convolutional Neural Networks (GCNs) have gained widespread popularity in various fields like personal healthcare and financial systems, due to their remarkable performance. Despite the growing demand for cloud-based GCN services, privacy concerns over sensitive graph data remain significant. Homomorphic Encryption (HE) facilitates Privacy-Preserving Machine Learning (PPML) by allowing computations to be performed on encrypted data. However, HE introduces substantial computational overhead, particularly for GCN operations that require rotations and multiplications in matrix products. The sparsity of GCNs offers significant performance potential, but their irregularity introduces additional operations that reduce practical gains. In this paper, we propose FicGCN, a HE-based framework specifically designed to harness the sparse characteristics of GCNs and strike a globally optimal balance between aggregation and combination operations. FicGCN employs a latency-aware packing scheme, a Sparse Intra-Ciphertext Aggregation (SpIntra-CA) method to minimize rotation overhead, and a region-based data reordering driven by local adjacency structure. We evaluated FicGCN on several popular datasets, and the results show that FicGCN achieved the best performance across all tested datasets, with up to a $4.10\times$ improvement over the latest design.
APA
Kan, Z., Han, H., Shi, S., Hua, T., Lu, H., Li, X., Mu, J. & Hu, X.. (2025). FicGCN: Unveiling the Homomorphic Encryption Efficiency from Irregular Graph Convolutional Networks. Proceedings of the 42nd International Conference on Machine Learning, in Proceedings of Machine Learning Research 267:28832-28848 Available from https://proceedings.mlr.press/v267/kan25a.html.

Related Material