BriefGPT.xyz
Oct, 2018
图神经网络在图划分中的平均场理论
Mean-field theory of graph neural networks in graph partitioning
HTML
PDF
Tatsuro Kawamoto, Masashi Tsubaki, Tomoyuki Obuchi
TL;DR
研究了图神经网络的理论性能分析，证明了其在分类任务中灵活性优势高于贝叶斯推断，并探讨了其高精度性能是由反向传播还是架构本身引起的问题。采用最小化图划分问题的平均场理论，证明了数值实验的良好一致性。
Abstract
A theoretical performance analysis of the
graph neural network
(GNN) is presented. For classification tasks, the neural network approach has the advantage in terms of
flexibility
that it can be employed in a data
→