Robust Preference Inference from Spatial-Temporal Interaction Networks

This project aims to develop innovative techniques for effectively and efficiently managing user preference profiles from less labelled, sparse and noisy interaction data. A unified novel learning framework along with a set of data analysis techniques are expected to be developed from this project, which will provide a non-intrusive way of conducting predictive analysis on user preference profiling via discovering human explicit and implicit interest domains. The expected results of this application will not only maintain Australia's leadership in this frontier
research area, but also support many important applications that safeguard Australian people and economy such as cyber security, healthcare, and e-Commerce.