Presenter: Dr. Dejing Dou
Title: Deep Learning and Privacy Preserving in a Health Social Network

Abstract: Modeling and predicting human behaviors is the key to help spread wellness in a health social network. The YesiWell system was built to collect data for 254 obese or over weight users with their one year physical activities, social communications, and biomarkers/biometrics. The user diversity, dynamic behaviors, and hidden social influences make the problem very challenging. In this talk, I first introduce our novel deep learning approach for human behavior prediction in YesiWell health social network. Then I discuss the obvious privacy issues when applying deep learning in the health domain. Our main idea for privacy preserving is to enforce differential privacy by perturbing the objective functions of deep learning models, such as deep auto-encoder, rather than its results. Theoretical analysis and thorough experimental evaluations show that our approach is highly effective and efficient.

Bio: Dejing Dou is a Professor in the Computer and Information Science Department at the University of Oregon and leads the Advanced Integration and Mining (AIM) Lab. He received his bachelor degree from Tsinghua University, China in 1996 and his Ph.D. degree from Yale University in 2004. His research areas include artificial intelligence, data mining, data integration, information extraction, and health informatics. Dejing Dou has published more than 80 research papers, some of which appear in prestigious conferences and journals like AAAI, KDD, ICDM, SDM, CIKM, ISWC, JIIS, and JoDS. His DEXA’15 paper received the best paper award. His KDD’07 paper was nominated for the best research paper award. He is on the Editorial Boards of Journal on Data Semantics, Journal of Intelligent Information Systems, and PLUS ONE. He has been serving as program committee members for various international conferences and as program co-chairs for four of them. Dejing Dou has received over $4.5 million PI research grants from the NSF and the NIH.