A0927
Title: Spectral co-clustering in multi-layer Directed networks
Authors: Wenqing Su - Tsinghua University (China) [presenting]
Ying Yang - Tsinghua University (China)
Abstract: Multilayer network data analysis is one of the research hotspots in statistics and biomedical. Current literature on multilayer network data is mostly limited to undirected relations. However, direct relations are more common and may introduce extra information. The focus is on community detection in multilayer-directed networks. To account for the asymmetry, a novel spectral-co-clustering-based algorithm is developed to detect co-clusters, which capture the sending patterns and receiving patterns of nodes, respectively. Specifically, the eigen-decomposition of the debiased sum of Gram matrices over the layer-wise adjacency matrices is computed, followed by the k-means, where the sum of Gram matrices is used to avoid possible cancellation of clusters caused by direct summation. Theoretical analysis of the misclassification rates is derived, which shows that multilayers would benefit clustering performance. The experimental results of simulated data corroborate the theoretical predictions, and the analysis of a real-world trade network dataset provides interpretable results.
