Active Transfer Learning for Recommendation

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


PhD Thesis Defence


Title: "Active Transfer Learning for Recommendation"

By

Miss Lili ZHAO


Abstract

A long-standing goal of recommender system is to solve data sparsity issue, 
where user-item preference data is not enough to train a reliable model. 
Significant strides have been made towards to this goal over the last few years 
thanks to the fast-moving in the field of data gathering, algorithms and 
computing infrastructure. The progress has been especially rapid in offering 
context information going beyond user-item preferences. The context information 
can be divided into two categories in terms of its resources type:  attribute 
information associated with users and items, and cross-domian knowledge 
concerning data from different but related domain. By developing methods that 
can effectively utilize context information for recommendation task, 
performance can be enhanced further.

In the first part of this dissertation, we consider the problem of improving 
recommendation with in-domain context data. In movie recommendation, it is 
often the case that movie posters and stills provide us with rich knowledge for 
understanding movies as well as users’ preferences. For instance, user may want 
to watch a movie at the minute when she/he finds some released posters or still 
frames attractive. Unfortunately, such unique features cannot be revealed from 
rating data or other forms of context being used in most of existing methods. 
To address this, we formulate a flexible, discriminative model that is able to 
model both bias and regularizations by considering such features, resulting in 
a better understanding of movie preferences and improved recommendation 
performance.

The second part of this dissertation tackles the problem of cooperating 
cross-system knowledge in recommendation. Transfer learning techniques have 
demonstrated promising successes in this direction. However, despite much 
encouraging progress, most of the advances in transfer learning still take 
place in the condition of fully entity correspondences between two systems. The 
nature of cross-system recommendation compels us to move beyond the existing 
paradigm of transfer learning to develop novel algorithms. Towards this end, we 
build methods and techniques for general transfer learning in cross-system 
recommendation settings, which allow us to loose the condition of "fully 
corresponded" entities as input, enabling to construct entity correspondence 
with limited budget by using active learning strategy to facilitate knowledge 
transfer across recommender systems. In particular, first we propose a unified 
framework for cross-domain recommendation. This framework allows us to identify 
correspondences that can bring as much knowledge as possible, then we can 
conduct efficient transfer model to improve recommendation quality. Second, 
based on the framework, we develop three solutions that iteratively select 
entities in the target system based on our proposed criterion to query their 
correspondences in the source system. We demonstrate that these solutions can 
take advantage of active learning techniques, lead to many practical benefits.


Date:			Wednesday, 16 September 2020

Time:			2:00pm - 4:00pm

Zoom Meeting:		https://hkust.zoom.us/j/7866795682

Chairperson:		Prof. Bing-yi JING (MATH)

Committee Members:	Prof. Qiang YANG (Supervisor)
 			Prof. Kai CHEN
 			Prof. Yangqiu SONG
 			Prof. Weichuan YU (ECE)
 			Prof. Jiannong CAO (PolyU)


**** ALL are Welcome ****