The growth of Graph Convolution Network (GCN) model sizes has revolutionized numerous applications, surpassing human performance in areas such as personal healthcare and financial systems. The deployment of GCNs in the cloud raises privacy concerns due to potential adversarial attacks on client data. To address security concerns, Privacy-Preserving Machine Learning (PPML) using Homomorphic Encryption (HE) secures sensitive client data. However, it introduces substantial computational overhead in practical applications. To tackle those challenges, we present LinGCN, a framework designed to reduce multiplication depth and optimize the performance of HE based GCN inference. LinGCN is structured around three key elements: (1) A differentiable structural linearization algorithm, complemented by a parameterized discrete indicator function, co-trained with model weights to meet the optimization goal. This strategy promotes fine-grained node-level non-linear location selection, resulting in a model with minimized multiplication depth. (2) A compact node-wise polynomial replacement policy with a second-order trainable activation function, steered towards superior convergence by a two-level distillation approach from an all-ReLU based teacher model. (3) an enhanced HE solution that enables finer-grained operator fusion for node-wise activation functions, further reducing multiplication level consumption in HE-based inference. Our experiments on the NTU-XVIEW skeleton joint dataset reveal that LinGCN excels in latency, accuracy, and scalability for homomorphically encrypted inference, outperforming solutions such as CryptoGCN. Remarkably, LinGCN achieves a 14.2x latency speedup relative to CryptoGCN, while preserving an inference accuracy of 75% and notably reducing multiplication depth.

翻译：图卷积网络模型规模的扩展已彻底改变众多应用领域，在个人医疗及金融系统等领域中超越了人类表现。GCN在云端的部署因潜在的对客户端数据的对抗性攻击而引发隐私担忧。为应对安全问题，采用同态加密的隐私保护机器学习可保护敏感的客户端数据，但会为实际应用引入显著计算开销。针对上述挑战，我们提出LinGCN框架，旨在降低乘法深度并优化基于HE的GCN推理性能。LinGCN围绕三个关键要素构建：（1）可微分结构线性化算法，辅以参数化离散指示函数，与模型权重协同训练以达成优化目标。该策略促进细粒度的节点级非线性位置选择，从而生成具有最小化乘法深度的模型。（2）紧凑的节点级多项式替代策略，配备二阶可训练激活函数，通过基于全ReLU教师模型的两级蒸馏方法引导其实现优越收敛。（3）增强型HE解决方案，可实现节点级激活函数更细粒度的算子融合，进一步降低基于HE推理中的乘法层级消耗。我们在NTU-XVIEW骨架关节点数据集上的实验表明，LinGCN在同态加密推理的延迟、准确率和可扩展性方面表现优异，优于CryptoGCN等方案。值得注意的是，LinGCN相对于CryptoGCN实现了14.2倍的延迟加速，同时保持75%的推理准确率并显著降低了乘法深度。