Build probabilistic generative models for unifying the analyses of the latent structures and correspondence in human-generated text data and behavior data to get a comprehensive understanding of users' underlying intents. Read More
Organize users' longitudinal information seeking activities into tasks, and develop online learning algorithms to proactively infer users intents and dynamically adapt the systems from interactions with humans for long-term optimality. Read More
Estimate the sensor data of one building based on sensor data collected in other buildings. The basic premise is that common design and construction patterns for buildings create a repeating structure in their sensor data. Read More
Create a suite of automated mapping solutions that will allow an analytics engine to quickly connect to and analyze the data from an unfamiliar building. This research enables building analytics to be applied at scale. Read More
Provide meaningful privacy guarantees by obfuscating users' search behaviors via probabilistic generative models, and develop algorithmic methods to evaluate the cost and privacy benefits of different obfuscation techniques. Read More
Our group is comprised of graduate, undergradaute, and visiting researchers in computer science. We collaborate with researchers from institutes and universities worldwide on various projects.
December 13, 2017
Our project of "The Building Adapter: Automatic Mapping of Commercial Buildings for Scalable Building Analytics" in a collaboration with Dr. Kamin Whitehouse has been funded by the U.S. Department of Energy under the BENEFIT program. More details can be found here.
Novemeber 7, 2017
One paper got accepted by AAAI 2018 for cross region energy disaggregation via transfer learning.
August 5, 2017
Two papers got accepted by CIKM 2017, one for optimization of user engagement and one for student behavior modeling in Massive Online Open Courses.
June 15, 2017
We have been awarded as the winner of Yelp Dataset Challenge Round 8.
April 10, 2017
Our project of "Cyber Physical Mappings - Empower Building Analytics at Scale" in a collaboration with Dr. Kamin Whitehouse has been funded by the National Science Foundation under the III Small program. More details about this award can be found here.
April 10, 2017
Two papers got accepted by SIGIR 2017, one for modeling topical correspondence in text documents and one for a demo system of aspect-based review mining.
December 19, 2016
One paper got accepted by WWW 2017 for personalized sentiment analysis with non-parameteric Bayesian clustering.
November 12, 2016
Two papers got accepted by AAAI-2017: one for online collaborative recommendation and one for collaborative sensing.
October 1, 2016
Our project of "Collaborative Sensing: An Approach for Immediately Scalable Sensing in Buildings" in a collaboration with Dr. Kamin Whitehouse has been funded by NSF CPS program. More details about this award can be found here.
August 30, 2016
Our project of "Privacy-Preserving Personalization" in a collaboration with Dr. David Evans and Dr. Denis Nekipelov has been funded by the School of Engineering's Cybersecurity Initiative.
July 12, 2016
Our project of "Collaborative Learning with Incomplete and Noisy Knowledge" in a collaboration with Dr. Quanquan Gu has been funded by NSF III program. More details about this award can be found here.
May 13, 2016
Lin Gong has been awared for the Presidential Fellowships in Data Science. Congratulations!
December 30, 2015
Hongning Wang has received the NSF Faculty Early Career Development Program (CAREER) Award. More details about this award can be found here.
December 21, 2015
Our proposal of "Call for Special Issue on Search, Mining and their Applications on Mobile Devices" has been accepted by the ACM Transactions on Information Systems (TOIS). Call for papers will be announced shortly.