Collective diffusion over networks: Models and inference

Diffusion processes in networks are increas-ingly used to model the spread of informa-tion and social influence. In several applica-tions in computational sustainability such as the spread of wildlife, infectious diseases and traffic mobility pattern, the observed data of-ten consists of only aggregate information. In this work, we present new models that gener-alize standard diffusion processes to such col-lective settings. We also present optimization based techniques that can accurately learn the underlying dynamics of the given conta-gion process, including the hidden network structure, by only observing the time a node becomes active and the associated aggregate information. Empirically, our technique is highly robust and accurately learns network structure with more than 90 % recall and pre-cision. Results on real-world flu spread data in the US confirm that our technique can also accurately model infectious disease spread.