Heterogeneous Transfer Learning

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Heterogeneous Transfer Learning"

By

Miss Ying WEI


Abstract

Artificial Intelligence has been enjoying an unprecedented boom recently. The 
huge success, however, still heavily depends on massive labeled data. Transfer 
learning, leveraging knowledge from a source domain to improve predictive 
models in a target domain which does not have sufficient labeled data, has been 
more and more popular. In transfer learning, a source and a target domain have 
a discrepancy in any of the feature space, distribution, label space, and 
predictive models, which traditional machine learning algorithms cannot handle. 
The majority of existing transfer learning algorithms focus on homogeneous 
transfer learning where the feature space, the label space as well as the 
predictive model are shared. However, homogeneous transfer learning algorithms 
lose their power if the shared feature space is insufficient to build 
satisfactory predictive models, or if a source domain in the same feature and 
label space cannot be found. In this case, heterogeneous transfer learning 
(HTL) is desired. Provided with a source domain in a completely different 
feature space or label space, heterogeneous transfer learning algorithms 
transfer knowledge in different perspectives, just as we human beings with a 
multi-sensory system are capable of transferring lip reading knowledge to 
improve speech understanding if one is whispering in a very low voice.

The key to transfer learning is to building either instance-based or 
feature-based mappings between a source and a target domain. In this thesis, we 
focus on developing scalable and principled methodologies to build feature 
mappings under different heterogeneity: 1) how to build semantic correspondence 
between a pair of source and target domains in different feature spaces to pave 
the way for successful knowledge transfer; 2) how to transfer when a source and 
a target domain have different feature spaces, while each domain has either 
single type of data or multiple types of data; 3) how to transfer when a source 
and a target domain have different label spaces. We have applied our algorithms 
to multiple large-scale real-world datasets from different applications 
including computer vision, social media, health care, and urban computing. This 
thesis introduces this research frontier and points out some promising research 
issues for extensive investigation.


Date:			Monday, 31 July 2017

Time:			2:30pm - 4:30pm

Venue:			Room 2612A
 			Lifts 31/32

Chairman:		Prof. Yu-Hang Chao (MAE)

Committee Members:	Prof. Qiang Yang (Supervisor)
 			Prof. Lei Chen
 			Prof. Dit-Yan Yeung
 			Prof. Yang Wang (MATH)
 			Prof. Le Song (Computing, Georgia Inst. of Tech.)


**** ALL are Welcome ****