Thursday, December 12, 2019 - 10:00 to 11:30
SCHOOL OF COMPUTER SCIENCE
The School of Computer Science at the University of Windsor is pleased to present …
PhD. Seminar by: Fen Zhao
Date: Thursday December 12, 2019
Time: 10:00 am-11:30am
Location: Lambton Tower 3105
Abstract:
In scholarly data, authors are connected via collaboration and further linked by citation links between papers, forming a heterogeneous network that contains richer information than homogeneous networks. This seminar studies author embeddings on such a heterogeneous network that contains citation and co-authorship links.
We first discuss the difference between heterogeneous and homogeneous networks. Then we experiment with two large real-world datasets in the domain of Computer Science and Health. After obtaining the author embeddings by DeepWalk, we conduct experiments and show that author embeddings learned from heterogeneous graph have similar performance as homogeneous networks in the classification task, and is better in the clustering task. We also build a similarity search engine to explore the relationship between authors in Computer Science.
Thesis Committee:
Internal Reader: Dr. Arunita Jaekel, Dr. Peter Tsin
External Reader: Dr. Abdulkadir Hussein
Advisor: Dr. Jianguo Lu
PhD Seminar Announcement
5113 Lambton Tower, 401 Sunset Ave., Windsor ON, N9B 3P4 (519) 253-3000 Ext. 3716 csgradinfo@uwindsor.ca