TL;DR本文提出了一种基于路径积分方法的最大熵转移矩阵,称为 PAN 框架,该框架替代了通常用于图结构数据的图拉普拉斯卷积,可以有效提高图神经网络的学习效果和收敛速度,同时在基准测试任务上达到了最先进的性能水平。
Abstract
Convolution operations designed for graph-structured data usually utilize the
graph Laplacian, which can be seen as message passing between the adjacent
neighbors through a generic random walk. In this paper, we propose PAN, a new
graph convolution framework that involves every path li