LoNe Sampler: 通过协调局部邻居采样生成图节点嵌入

Nov, 2022

LoNe Sampler: 通过协调局部邻居采样生成图节点嵌入

LoNe Sampler: Graph node embeddings by coordinated local neighborhood sampling

Konstantin Kutzkov

TL;DRLoNe Sampler提供了一套算法来生成离散化的节点嵌入，通过本地邻域采样，并解决了之前工作的两个缺点，实验结果在基准数据集上验证理论发现并证明了所提出方法的优点。

Abstract

local graph neighborhood sampling is a fundamental computational problem that is at the heart of algorithms for node representation learning. Several works have presented algorithms for learning →