Description
The purpose of this graduate-level course is introducing a distributed application system and understanding the related issues. In this semester, the main topic of this course is a recommender system. The course covers the essential of recommender systems such as recommendation techniques (collaborative, content-based, knowledge-based and hybrid) and evaluation methods, as well as exploring some further issues such as security issues, online market decision making process, recommendation systems in next generation web or IoT/ubiquitous environment. Also, this course intend that students catch up the recent research issues related to recommender systems. Extensive paper reading/presentation assignments and a project related to recommender systems will be issued.
Instructor
Kyungbaek Kim
Office : Engineering Building #6, 715
Tel : +82-62-530-3438
Email : kyungbaekkim@jnu.ac.kr
Office Hours : Wed 10:00 ~ 10:45
Time and Location
Thur 9:00-11:30, Engineering Building #6, 106
Textbook
- Recommender Systems : An Introduction, by Dietmar Jnnach, Markus Zanker, Alexander Felfering, and Gerhard Friedrich
Grading Policy
- Attendance : 10%
- Reading Assignments and exercises : 30%
- Tentatively Two papers per week : 13 papers
- Hadoop exercises
- Projects : 30%
- Personal Project : research on Hadoop related projects
- Team Project
- Exam : 30%
Lecture Notes
Lecture notes are accessible through the eClass of JNU portal.
- Syllabus
- 1.Introduction
- 2.Collaborative recommendation
- 3.Content-based recommendation
- 4.Knowledge-based recommendation
- 5.Hybrid recommendation approaches
Homeworks, Quiz, Midterm/Final Exam
All of the materials related to homeworks, quiz, midterm exam and final exam, including solutions, are accessible through the eClass of JNU portal.
Exercise of Recommender System
Reading Assignment
Submit the summary of given reading assignments on the due date.
- Due on 11th March
- Due on 18th March
- Due on 25th March
- Due on 1st April
- Due on 8th April
- Due on 15th April
- Due on 29th April
- Due on 6th May
- Due on 13th May
- Due on 20th May
- Due on 27th May
- Due on 3rd June
- Due on 10th June
Paper Presentation
- [CIKM_2013] Location Recommendation for Out-of-Town Users in Location-Based Social Networks
- [CIKM_2013] GAPfm Optimal Top-N Recommendations for Graded Relevance Domains
- [CIKM_2013] Community-Based User Recommendation in Uni-Directional Social Networks
- [ICDE_2013] Focused Matrix Factorization For Audience Selection in Display Advertising
- [KDD_2013] FISM factored item similarity models for top-N recommender systems
- [KDD_2013] LCARS a location-content-aware recommender system
- [KDD_2013] Learning geographical preferences for point-of-interest recommendation
- [WWW_2014] A Monte Carlo Algorithm for Cold Start Recommendation
- [WWW_2014] Local collabarative ranking
- [WWW_2014] Personalized Collaborative Clustering
- [WWW_2014] Temporal QoS-Aware Web Service Recommendation via Non-negative Tensor
- [CIKM_2014] Graph-based Point-of-interest Recommendation with Geographical and Temporal Influences
- [CIKM_2014] Meta-Path-Based Ranking with Pseudo Relevance Feedback on Heterogeneous Graph for Citation Recommendation
- [CIKM_2014] On Improving Co-Cluster Quality with Application to Recommender Systems
- [CIKM_2014] User Interests Imbalance Exploration in Social Recommendation- A Fitness Adaptation
- [ICDE_2014] CrowdPlanner- A Crowd-Based Route Recommendation System
- [ICDE_2014] Efficient Instant-Fuzzy Search with Proximity Ranking
- [ICDE_2014] Exploiting group recommendation functions for flexible preferences
- [ICDE_2014] Ranking Item Features by Mining Online User-Item Interactions
- [KDD_2014] Jointly Modeling Aspects, Ratings and Sentiments for Movie Recommendation (JMARS)
- [KDD_2014] Matching Users and Items Across Domains to Improve the Recommendation Quality
- [KDD_2014] Optimal Recommendations under Attraction, Aversion, and Social Influence
- [KDD_2014] GeoMF- Joint Geographical Modeling and Matrix Factorization for Point-of-Interest Recommendation
- [KDD_2014] Product Selection Problem- Improve Market Share by Learning Consumer Behavior
- [SIGIR_2013] Time-aware Point-of-interest Recommendation
- [SIGIR 2014] Addressing Cold Start in Recommender Systems A Semi-supervised Co-training Algorithm
- [SIGIR 2014] Explicit Factor Models for Explainable Recommendation based on Phrase-level Sentiment Analysis
- [SIGIR 2014] Gaussian Process Factorization Machines for Context-aware Recommendations
Date |
Student |
Paper |
Slides |
2015-April-09 |
|
|
|
2015-April-16 |
|
|
|
2015-April-30 |
|
|
|
2015-May-07 |
|
|
|
2015-May-14 |
|
|
|
2015-June-04 |
Zubair |
Afaq |
Fiqri |
Nhat |
Priagung |
Alvin |
|
|
|
2015-June-11 |
Lesley |
Gemoh |
Gde |
Tiep |
Rajashree |
Ngoc |
Duong |
|
|
|
Project
Team # |
Members |
Title |
1 |
Rajashree, Tiep, Lesley, Gemoh |
Graph-based interested user recommendation by using geo-social data |
2 |
Nhat, Ngoc, Duong |
Solving Sparsity Challenges in Collaborative Filtering System |
3 |
Fiqri, Alvin, Priagung, Gde |
Soft-thresholded SVD Recommender Application Using "softImpute" library on R |
4 |
Zubair, Afaq |
Summary on hybrid recommendation approaches |