LinGCN：面向同态加密推理的结构线性化图卷积网络
LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference
AI总结：
针对同态加密下GCN推理计算开销大的问题，提出LinGCN框架，通过结构线性化、多项式激活替换与增强HE方案降低乘法深度，在NTU-XVIEW数据集上延迟较CryptoGCN提升14.2倍且保持75%准确率。
摘要：
图卷积网络（GCN）模型规模的增长已为众多应用带来变革，在个人医疗、金融系统等领域的表现超越人类水平。将GCN部署在云端会引发隐私担忧，因为客户端数据可能遭受对抗性攻击。为解决安全问题，采用同态加密（HE）的隐私保护机器学习（PPML）可保护敏感客户端数据，但这会在实际应用中带来巨大的计算开销。为应对这些挑战，我们提出LinGCN，这是一个旨在降低乘法深度、优化基于HE的GCN推理性能的框架。LinGCN围绕三个核心要素构建：（1）可微结构线性化算法，辅以参数化离散指示函数，与模型权重共同训练以达成优化目标。该策略支持细粒度的节点级非线性位置选择，最终得到乘法深度最小化的模型。（2）紧凑的逐节点多项式替换策略，搭配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实现更优收敛。（3）增强的HE方案，支持对逐节点激活函数进行更细粒度的算子融合，进一步降低基于HE的推理中的乘法层级消耗。我们在NTU-XVIEW骨架关节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的延迟速度是CryptoGCN的14.2倍，同时保持75%的推理准确率，并显著降低了乘法深度。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
