[ 정보통신종합설계 ] 제5차 전문가 초청 세미나 안내
technology and applications
연사: 김상욱 교수, 한양대학교
일시: 11월 2일(수) 오후 4시
장소: 60주년 기념관, 106호
As the number of online items significantly grows, it becomes a difficult task for users to find those items on their own. Good matching of users to suitable items is critical to enhance user satisfaction, which highlights the importance of recommendation systems. The recommendation systems analyze users’ behavioral characteristics, predicting the items with which a user would be truly satisfied. The approaches to recommendation systems are classified into two categories: content based and collaborative filtering (CF) based approaches. The CF-based approach selects items to be recommended to a target user by analyzing those items preferred by his/her neighbors whose preference is similar to that of the target user. In this talk, we introduce CF-based recommendation systems and address how to improve the accuracy and running time of top-N recommendation with CF.
Unlike existing works that use only the rated items (which is only a small fraction in a rating matrix), we propose the notion of pre-use preferences of users towards a vast amount of unrated items. Using this novel notion, we effectively identify uninteresting items that were not rated yet are likely to receive very low ratings from users, and impute them as zero in a rating matrix. This simple-yet-novel zero-injection applied to a set of carefully-chosen uninteresting items not only addresses the well-known data sparsity problem by enriching a rating matrix but also completely prevents uninteresting items from being recommended as top-N items, thereby improving accuracy greatly. As our proposed idea is method-agnostic, it can be easily applied to a wide variety of popular CF approaches. Through comprehensive experiments using the Movie lens dataset and My Media Lite implementation,
we demonstrate that our solution consistently and universally improves the accuracies of popular CF approaches (e.g., item-based CF, SVD-based CF, and SVD++) by two to five orders of magnitude on average. Furthermore, our solution reduces the running time of those CF methods by 1.2 to 2.3 times when its setting produces the best accuracy.
Prof. Sang-Wook Kim received the B.S. degree in Computer Engineering from Seoul National University, Korea at 1989, and earned the M.S. and Ph.D. degrees in Computer Science from Korea Advanced Institute of Science and Technology (KAIST), Korea at 1991 and 1994, respectively.
From 1995 to 2003, he served as an Associate Professor of the Division of Computer, Information, and Communications Engineering at Kangwon National University, Korea. In 2003, he joined Hanyang University, Seoul, Korea, where he currently is a Professor at the Department of Computer Science and Engineering and the director of the Brain-Korea-21-Plus research program. He is also leading a National Research Lab (NRL) Project funded by National Research Foundation from 2015. His research interests include databases, data mining, multimedia information retrieval, social network analysis, recommendation, and web data analysis.
문의처: 정보통신공학과 박재형 교수 (firstname.lastname@example.org 교내 7432)
전 학년생 대상이며 일부 과목에서는 “수업 외 교과활동”으로 인정 가능 (각 과목별로 문의)
정보통신공학과 정보통신프로젝트 수강생은 전회 필수 참석