BriefGPT.xyz
Nov, 2023
一种用于半监督图学习的一致性扩散算法
A Consistent Diffusion-Based Algorithm for Semi-Supervised Graph Learning
HTML
PDF
Thomas Bonald, Nathan de Lara
TL;DR
半监督分类的目标是基于所知少数节点（称为种子）的标签来为图的所有节点分配标签。本文证明了在计算得分之前需要对节点的温度进行居中处理，否则该算法是不一致的。这一关键步骤不仅使得算法在块模型上可以证明是一致的，还在实际图上带来了显著的性能提升。
Abstract
The task of
semi-supervised classification
aims at assigning labels to all nodes of a
graph
based on the labels known for a few nodes, called the seeds. One of the most popular algorithms relies on the principle
→