ABSTRACT
In disease-dedicated social networking sites and online support groups, it is common for the users to stick to one disease-specific social network, although their desired resources are spread over multiple social networks, such as patients with similar questions and concerns. Motivated by this application, we focused on cross-network link recommendation, which aims to identify similar actors across multiple heterogeneous social networks. Also, in these networks the content evolves over time, thereby the distribution of features and labels also vary over time. There is a need for algorithms that can address this issue of distribution shift. Finally, modeling user behavior in these cross-network settings can help in various machine learning tasks. In this chapter we propose various algorithms to address the above mentioned problems.
