Networks (i.e., graphs) appears in many high-impact applications. Often these networks are collected from different sources, at different times, at different granularities. In this talk, I will present our recent work on mining such multiple networks. First, we will present several new data models, whose key idea is to leverage networks as context to connect different data sets or different data mining models, including a network of networks (NoN) model, a network of co-evolving time series (NoT) model and a network of regression model. Second, we will present some algorithmic examples on how to perform mining with such new models where the key idea is to leverage the contextual network as an effective regularizer during the mining process, including ranking, imputation, prediction and inference. Finally, we will demonstrate the effectiveness of our new models and algorithms in some applications, including bioinformatics, sensor networks, critical infrastructure networks and scholarly data mining.