Active Transfer Learning for Recommendation System

PhD Thesis Proposal Defence


Title: "Active Transfer Learning for Recommendation System"

by

Miss Lili ZHAO


Abstract:

A long-standing goal of recommendation 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-domain 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 proposal, 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 proposal 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, we propose an active learning strategy, which 
allows us to identify correspondences that can bring as much knowledge as 
possible, then we can conduct efficient transfer  model to improve 
recommendation quality. We demonstrate that these solutions can take 
advantage of active learning techniques, lead to many practical benefits.


Date:			Thursday, 10 September 2020

Time:                  	2:00pm - 4:00pm

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

Committee Members:	Prof. Qiang Yang (Supervisor)
  			Dr. Kai Chen (Chairperson)
 			Dr. Qiong Luo
 			Dr. Xiaojuan Ma


**** ALL are Welcome ****