摘要 Network data has attracted increasing research interests across variousscientific communities. In this talk, I will talk about some of our recentprojects on multi-layer networks, including change point detection and interlayer dependency. Particularly, I will introduce a new subspace trackingmethod to detect network subspace changes so as to assure homogeneousnetwork layers between adjacent change points, and also a new stochasticblock Ising model (SBIM) to accommodate intet-layer dependency amongthe neighboring homogeneous network layers. The developed methods aresupported by their asymptotic properties as well as a variety of real applications. If time permits, I will also briefly discuss about the compromisebetween privacy protection and estimation accuracy in multi-layer networks.
