Optimal Network Membership Estimation under Severe Degree Heterogeneity
研究了真实网络中节点度差异极大时，如何影响混合成员估计的统计极限，并提出了一个通过预PCA归一化步骤改进的谱算法，该算法在任意度异质性下都能达到最优估计速率。
Real networks often have severe degree heterogeneity, with maximum, average, and minimum node degrees differing significantly. This paper examines the impact of degree heterogeneity on statistical limits of network data analysis. Introducing the empirical heterogeneity distribution (EHD) under a degree-corrected mixed membership model, we show that the optimal rate of mixed membership estimation is an explicit functional of the EHD. This result confirms that severe degree heterogeneity decelerates the error rate, even when the overall sparsity remains unchanged.To obtain a rate-optimal method, we modify an existing spectral algorithm, Mixed-SCORE, by adding a pre-PCA normalization step. This step normalizes the adjacency matrix by a diagonal matrix consisting of the bth power of node degrees, for some b∈ℝ. We discover that b = 1/2 is universally favorable. The resulting spectral algorithm is rate-optimal for networks with arbitrary degree heterogeneity. A technical component in our proofs is entry-wise eigenvector analysis of the normalized graph Laplacian.