Home > Events > PhD Defense - Chuxu Zhang

PhD Defense - Chuxu Zhang

Start: 3/26/2020 at 10:50AM
End: 3/26/2020 at 1:30PM
Location: Remote via Zoom
Attendees: Remote attendance:
Meeting ID: 931 200 357. Those that will be joining remotely need to mute their microphones until the Q&A session begins. Please disconnect when the public portion ends.
Event Url: https://us04web.zoom.us/j/931200357
Add to calendar:
iCal vCal

Chuxu Zhang

Dissertation Defense

March 26, 2020      10:50 am      Remote via Zoom

Adviser:  Dr. Nitesh Chawla

Committee Members:

       Dr. David Chiang        Dr. Meng Jiang        Dr. Xiangliang Zhang 

Title:

"Learning from Heterogeneous Data"

Abstract:

In today’s information and computational society, complex systems (e.g., social network, e-commerce platform, cyber-physical system, chemical synthesis) are often associated with heterogeneous (multi-modal) data, such as structural relation/graph, unstructured text/image, or temporal context. The heterogeneous data provide opportunities for researchers and practitioners to understand complex systems more comprehensively but also pose challenges to discover knowledge from them. Besides the difficulty of extracting and representing useful information from the complex data, it is hard to fuse the extracted knowledge in a unified manner so as to facilitate various underlying applications. Can we develop artificial intelligence solutions to extract, represent, fuse knowledge from heterogeneous data so as to solve different problems in complex systems?

In this thesis, I develop a series of methodologies and algorithms for learning from heterogeneous data through fusion, which have been deployed and validated in a variety of real-world applications, e.g., recommender system, relevance search, graph embedding, anomaly detection. Extending from fusion learning, I further investigate the principles and methodologies for label-efficient fusion learning from heterogeneous data, with the emphasis on the applications of web personalization and knowledge graph reasoning.