提出针对图数据的联邦学习梯度反演方法，可高效还原私有分子图数据。
FedGIG: Graph Inversion from Gradient in Federated Learning
- 设计稀疏离散约束模块，保证重构图的结构特性
- 在分子数据集上重构精度显著优于现有方法
- 适用于保护图数据隐私的场景，如药物研发
近期研究表明，联邦学习（FL）易受梯度反演攻击（GIA）威胁，攻击者可从共享梯度中恢复私有训练数据。然而，现有方法主要针对密集连续数据（如图像或向量化文本），无法直接应用于稀疏离散的图数据。本文首次探究梯度反演对联邦图学习（FGL）的影响，提出专为图结构数据设计的新型攻击方法FedGIG。该方法包含邻接矩阵约束模块，确保重构图的稀疏性与离散性；以及子图重构模块，用于补全缺失的共通子图结构。在分子数据集上的大量实验表明，FedGIG在重构精度上显著优于现有GIA技术。
原文摘要 · Abstract (English)
Recent studies have shown that Federated learning (FL) is vulnerable to Gradient Inversion Attacks (GIA), which can recover private training data from shared gradients. However, existing methods are designed for dense, continuous data such as images or vectorized texts, and cannot be directly applied to sparse and discrete graph data. This paper first explores GIA's impact on Federated Graph Learning (FGL) and introduces Graph Inversion from Gradient in Federated Learning (FedGIG), a novel GIA method specifically designed for graph-structured data. FedGIG includes the adjacency matrix constraining module, which ensures the sparsity and discreteness of the reconstructed graph data, and the subgraph reconstruction module, which is designed to complete missing common subgraph structures. Extensive experiments on molecular datasets demonstrate FedGIG's superior accuracy over existing GIA techniques.
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。