Network data is ubiquitous in the real-world, and many online websites providing various
kinds services can all be represented as networks, e.g., online social networks, e-commerce
networks, and academic networks. Learning and mining of network structured data have been
one of the most popular yet challenging research problems studied in recent years. For
example, how can we succinctly describe or summarize the characteristics of a person in a
social network based on his network connections or how do we determine that two persons play
similar roles in a social network? This project will study the problem of how to find a
simple, yet effective representation for each network node, which can capture its
characteristics or role in the network based on its connections. This is referred to as the
network embedding problem. As an effective tool to transform network data into classic
feature-vector representations, network embedding aims at mapping the network data into a
low-dimensional feature space, i.e., with a small number of features for each network node.
With the embedding results, all these aforementioned networks will be benefited to improve
their services provided for the public. This project focuses on developing a general network
embedding framework, and investigating its extension to application-oriented, multi-network
and dynamic-network scenarios. This project will help support female and minority students
to participate in academic research about network embedding. New network analytic tools will
be delivered, which are to be adopted in a new data mining curriculum delivered for both
undergraduate and graduate students at UIC and FSU. Research results dissemination is
planned via publication in relevant peer-reviewed top-tier conferences and journals.
