arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2412.18513cs.LGcs.CR
收藏

FedGIG:联邦学习中基于梯度的图反演

FedGIG: Graph Inversion from Gradient in Federated Learning

School of Computer Science and Technology, Huazhong University of Science and Technology(华中科技大学计算机科学与技术学院)

Tianzhe Xiao, Yichen Li, Yining Qi, Haozhao Wang, Ruixuan Li

AI总结:

本文首次探讨梯度反演攻击对联邦图学习的影响,提出专为图结构数据设计的FedGIG方法,通过邻接矩阵约束和子图重建模块恢复私有图数据,在分子数据集上准确率优于现有技术。

摘要:

近期研究表明,联邦学习(FL)容易受到梯度反演攻击(GIA),该攻击能从共享梯度中恢复私有训练数据。然而,现有方法专为图像或向量化文本等密集、连续数据设计,无法直接应用于稀疏且离散的图数据。本文首次探讨了GIA对联邦图学习(FGL)的影响,并提出了联邦学习中基于梯度的图反演(FedGIG),一种专为图结构数据设计的新型GIA方法。FedGIG包含邻接矩阵约束模块(确保重建图数据的稀疏性和离散性)以及子图重建模块(用于补全缺失的公共子图结构)。在分子数据集上的大量实验表明,FedGIG的准确率显著优于现有GIA技术。

英文摘要:

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.

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。

↑