Efficient Analysis of Latent Spaces in Heterogeneous Networks
提出一个统一框架，用于异质网络潜在空间模型的高效估计，通过识别共享潜在向量并利用高效得分方程提高统计效率，适用于多种边权重类型。
This work proposes a unified framework for efficient estimation under latent space modeling of heterogeneous networks. We consider a class of latent space models that decompose latent vectors into shared and network-specific components across networks. We develop a novel procedure that first identifies the shared latent vectors and further refines estimates through efficient score equations to achieve statistical efficiency. Oracle error rates for estimating the shared and heterogeneous latent vectors are established simultaneously. The analysis framework offers remarkable flexibility, accommodating various types of edge weights under general distributions.