Mining Personalized Data (in IoT devices)
Actually, the class is about recommender systems. Its name includes "IoT devices" but our lectures will not handle any issue about IoT. The course covers the basic concepts of recommender systems, including personalization algorithms, evaluation tools, and user experiences. We will discuss how recommender systems are deployed in e-commerce sites, social networks, and many other online systems. Additionally, we will study the recent research topic about recommendation in the industry and academy.
Everyone is required to read about 20 research papers through the course and present at least a recent work of recommender system.
Contact:
- Instructor: Younghoon Kim (nongaussian@gmail.com)
- TA: Woonghee Lee (woongheelee@hanyang.ac.kr)
IMPORTANT NOTICE
- Final exam: open book test (9:30am ~ 11:00am, Dec 18 at our regular class room)
- Bring your calcualtor that has log function
Presentation Schedule
Find the schedule below in Phase 2.
Phase 1: Traditional recommendation systems
Every week, 2~3 research papers will be handed out and the next week, we will have about-1.5-hours-long quiz asking questions about those reading matters. You can refer to copies of the reading material for quiz. That is, it is an open-book test.
Memory-based collaborative filtering & performance evaluation of recommendation systems (Quiz on Sep 18)
Badrul Munir Sarwar, George Karypis, Joseph A. Konstan, John Riedl: Item-based collaborative filtering recommendation algorithms. WWW 2001: 285-295
Y. Koren and R. Bell, “Advances in Collaborative Filtering,” Recommender Systems Handbook. Springer, 2011, Chapter 5, pp. 145-184.
G. Shani and A. Gunawardana, “Evaluating Recommendation Systems,” Recommender Systems Handbook. Springer, 2011, Chapter 8, pp. 257-294.
Model-based collaborative filtering (Quiz on Oct 2)
Koji Miyahara, Michael J. Pazzani: Collaborative Filtering with the Simple Bayesian Classifier. PRICAI 2000: 679-689
Albert Au Yeung: Matrix Factorization - A Simple Tutorial and Implementation in Python (blog article), http://www.albertauyeung.com/post/python-matrix-factorization/, 2017.
Yehuda Koren, Robert M. Bell, Chris Volinsky: Matrix Factorization Techniques for Recommender Systems. IEEE Computer 42(8): 30-37 (2009)
Y. Koren and R. Bell, “Advances in Collaborative Filtering,” Recommender Systems Handbook. Springer, 2011, Chapter 5, pp. 145-184.
Content-based collaborative filtering (Quiz on Oct 16)
Pasquale Lops, Marco de Gemmis, Giovanni Semeraro: Content-based Recommender Systems: State of the Art and Trends. Recommender Systems Handbook 2011: 73-105
Michael J. Pazzani, Daniel Billsus: Content-Based Recommendation Systems. The Adaptive Web 2007: 325-341
Phase 2: Deep-leaerning based recommendation systems
Every week, 2~3 students present 40min presentation. Research papers for your presentation will be picked from
Shuai Zhang, Lina Yao, Aixin Sun: Deep Learning based Recommender System: A Survey and New Perspectives. CoRR abs/1707.07435 (2017)
Oct. 23
김진희: Julian J. McAuley, Christopher Targett, Qinfeng Shi, Anton van den Hengel: Image-Based Recommendations on Styles and Substitutes. SIGIR 2015: 43-52
박준섭: Aäron van den Oord, Sander Dieleman, Benjamin Schrauwen: Deep content-based music recommendation. NIPS 2013: 2643-2651
Oct. 30
김영진: Developing a Twitter-based traffic event detection model using deep learning architectures
김종우: Deep Sequential Recommendation for Personalized Adaptive User Interfaces
Nov. 6
김문회: Neural Citation Network for Context-Aware Citation Recommendation
사미울라: Hashtag Recommendation Using Attention-Based Convolutional Neural Network
Nov. 13
(Complemental presentation) 김문회: Neural Citation Network for Context-Aware Citation Recommendation
오지강: A Neural Network Approach to Quote Recommendation in Writings
이브테삼무하마드: Comparative Deep Learning of Hybrid Representations for Image Recommendations
Nov. 20
천신: Embedding-based News Recommendation for Millions of Users
칸무하마드우메어: Collaborative Deep Learning for Recommender Systems
박승윤: Collaborative Recurrent Neural Networks for Dynamic Recommender Systems
Nov. 27
손수현: Representation Learning of Users and Items for Review Rating Prediction Using Attention-based Convolutional Neural Network
조용채: Deep Coevolutionary Network: Embedding User and Item Features for Recommendation
한군영: Neural Emoji Recommendation in Dialogue Systems
Dec. 4
쿤쳄소픽: Exploring Deep Space: Learning Personalized Ranking in a Semantic Space
사나나즈: Deep Content-User Embedding Model for Music Recommendation
Dec. 11
Dahal, Shubhechchha and Mygind, Hans Frederik Egeberg and Busek, Jakub: Tutorial on Microsoft Azure (e.g., Recommender System in Azure Machine Learning Studio)
Final exam (Dec 18)
The exam covers 3 quizs in Phase 1 and all papers presented in our class.