Data Fusion Reconstruction of Spatially Embedded Complex Networks

Abstract

We introduce a kernel Lasso (kLasso) optimization that simultaneously accounts for spatial regularity and network sparsity to reconstruct spatial complex networks from data. Through a kernel function, the proposed approach exploits spatial embedding distances to penalize overabundance of spatially long-distance connections. Examples of both synthetic and real-world spatial networks show that the proposed method improves significantly upon existing network reconstruction techniques that mainly concerns sparsity but not spatial regularity. Our results highlight the promise of data fusion in the reconstruction of complex networks, by utilizing both microscopic node-level dynamics (e.g., time series data) and macroscopic network-level information (metadata).