This colloquium has been postponed until further notice.
Join us as Hongyang Gao, PhD Candidate at Texas A&M University, presents "Graph Neural Networks: A Feature and Structure Learning Approach."
In the real world, many data are naturally represented as graph data such as social networks. Deep learning methods have been very successful in various fields such as computer vision and natural language processing. However, developing deep learning methods on graph data is challenging due to the lack of locality information. In this talk, Gao will present my work on developing deep learning methods on graph data. His work addresses this challenge and significantly advances feature learning and structure learning on graphs in both accuracy and efficiency.
Thursday, March 26 at 10:00 a.m. to 11:00 a.m.
Sennott Square, Seminar Room (5317)
210 South Bouquet Street, Pittsburgh, PA 15260