LSU CS Assistant Professor Receives NSF CAREER Award
May 19, 2020
BATON ROUGE, LA – LSU Computer Science and Engineering Assistant Professor Mingxuan Sun recently received the NSF CAREER Award for a project she is working on called “Privacy-aware Predictive Modeling of Dynamic Human Events,” which is supported by the NSF Information & Intelligent Systems Division. The grant, which runs from June 2020 to May 2025, is worth $422,815.
Over this course of time, Sun is expected to develop a series of novel models and algorithms to analyze dynamic human events. Machine learning that leverages individuals’ event data can improve the prediction accuracy of future events but introduces high risks to each individual’s privacy.
“Nowadays, large volumes of human event data, such as online TV-viewing records, domain name server queries, and electronic records of hospital admissions are becoming increasingly available in a wide variety of applications, including network analysis and services and healthcare analytics,” Sun said. “Predictive modeling of those collective event sequences is beneficial for promoting nationwide economic and safety development.”
For example, in network traffic diagnosis, the analysis of user activities can be used to predict and control dynamic traffic demand, which improves risk response efficiency. In health informatics, the analysis of patient admission events can detect and optimize treatment for individuals at risk, which enhances public health preparedness and healthcare outcomes. However, machine learning algorithms trained on historic event data may amplify privacy risks.
“Studies have demonstrated that it is possible to infer private attributes, such as demographics and locations from human activities such as online browsing histories and location check-in events,” Sun said. “This project is to develop a trusting-based machine learning framework that better protects human privacy while minimally impacting utility for predicting dynamic events.”
The project has three main points of research, the first of which is to investigate novel point processes, multi-view learning and deep learning methods for analyzing dynamic human events with event marker information.
“Besides time-stamped event sequences, additional marker information such as event types and tags can be utilized to better capture the dependencies between events,” Sun said.
The second point of research is to improve human understanding and trust of predictive modeling. In order to do this, interpretable algorithms will be developed to explain how their information is used in prediction and what potential private information can be inferred based on their input.
The third point of research is to balance privacy and utility, which benefits individuals and service providers.
“These three research aims are complemented by a comprehensive evaluation in a number of application domains,” Sun said.
Contact: Libby Haydel