BriefGPT.xyz
May, 2019
组合问题的图神经网络的近似比
Approximation Ratios of Graph Neural Networks for Combinatorial Problems
HTML
PDF
Ryoma Sato, Makoto Yamada, Hisashi Kashima
TL;DR
该论文从理论角度研究了如何利用图神经网络解决组合问题的近似算法，并提出了一种新的GNN类别，揭示了GNN的相对近似比，并证明了在节点特征中添加染色可以提高学习算法的近似比。
Abstract
In this paper, from a theoretical perspective, we study how powerful
graph neural networks
(GNNs) can be for learning
approximation algorithms
for
→