HONG KONG BAPTIST UNIVERSITY
FACULTY OF SCIENCE

Department of Computer Science Seminar
2020 Series

Interpretability in Data Mining: From Post-Hoc Analysis to Interpretable Modeling

Mr. Ninghao Liu
PhD Candidate
Department of Computer Science and Engineering
Texas A&M University (USA)

Date: October 15, 2020 (Thursday)
Time: 10:00 - 11:00 am
Venue: Zoom ID: 963 8159 2192
(The password and direct link will only be provided to registrants)

Registration: https://bit.ly/sem-zm
(Deadline: 2:00pm, 14 October 2020)

Abstract
Machine learning models have been widely applied in data mining due to their unprecedented prediction capabilities. However, machine learning is often criticized as a “black box” due to its opacity. To tackle the issue, interpretation techniques are needed to understand the working mechanism of models. Interpreting machine learning models, especially deep models, in data mining tasks is a challenging problem, because: (1) the definition is vague for model interpretation, (2) the structures and information processing paths are convoluted for complex models. I propose to tackle the problem in four aspects. First, given a black-box model, a fundamental requirement of interpretation is to attribute its prediction to important features. Second, I propose to understand the global latent representations learned by the model to extract structural knowledge. Third, I develop interpretable network embedding models via disentangling latent representations. Fourth, interpretation could be applied to model improvement, as well as to benefit anomaly detection and health informatics.

Biography
Ninghao Liu is a PhD candidate at the Department of Computer Science and Engineering of Texas A&M University. He received his M.Sc. degree from the School of Electrical and Computer Engineering at Georgia Institute of Technology in 2015, and B.Eng. degree from the School of Electronic and Information Engineering at South China University of Technology in 2014. His research interests include explainable artificial intelligence, network analysis and anomaly detection.

********* ALL INTERESTED ARE WELCOME ***********
(For enquiry, please contact Computer Science Department at 3411 2385)

http://www.comp.hkbu.edu.hk/v1/?page=seminars&id=563&lang=sc