A Survey on Session-based Recommendation

PhD Qualifying Examination


Title: "A Survey on Session-based Recommendation"

by

Mr. Tianwen CHEN


Abstract:

With the explosive growth of information, recommender systems (RSs) have become 
a critical tool to alleviate the information overload problem in many online 
services such as e-commerce and media sharing websites. Recently, session-based 
recommendation systems (SBRSs) have emerged as a new paradigm of RSs and 
received much attention in both academia and industry. Different from 
conventional RSs such as collaborative filtering-based RSs which rely on 
tracking user identities to model users' static long-term preferences, SBRSs do 
not require user information but learn users' dynamic short-term preferences by 
exploiting contextual information in anonymous sessions such as item 
co-occurrence patterns. Thus, SBRSs are more privacy-preserving and could 
provide more timely and accurate recommendations, which gives them highly 
practical value but also poses great challenges. In this survey, we offer a 
systematic review of session-based recommendation by presenting and comparing 
some representative works. In addition, we discuss the limitations of existing 
works and propose some possible future research directions.


Date:			Thursday, 19 August 2021

Time:                  	2:00pm - 4:00pm

Zoom meeting:
https://hkust.zoom.us/j/91340939907?pwd=Qmlnc05zWmpuaHRFNm1URVJKM0w3QT09

Committee Members:	Prof. Raymond Wong (Supervisor)
 			Prof. Gary Chan (Chairperson)
 			Prof. James Kwok
 			Prof. Nevin Zhang


**** ALL are Welcome ****