BriefGPT.xyz
Jul, 2023
带有特征和邻接矩阵对齐的强健图结构学习
Robust Graph Structure Learning with the Alignment of Features and Adjacency Matrix
HTML
PDF
Shaogao Lv, Gang Wen, Shiyu Liu, Linsen Wei, Ming Li
TL;DR
本研究提出了一种用于学习图结构的新型正则化方法,该方法采用节点级别雷德马赫复杂度的下界来对齐特征信息和图信息,同时结合稀疏降维使用低维节点特征,实现了对受噪声干扰的图结构的精确处理,并在真实世界数据集上进行了广泛实验。
Abstract
To improve the robustness of
graph neural networks
(GNN),
graph structure learning
(GSL) has attracted great interest due to the pervasiveness of noise in graph data. Many approaches have been proposed for GSL to
→