Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 김상욱 | - |
dc.date.accessioned | 2020-03-04T02:37:27Z | - |
dc.date.available | 2020-03-04T02:37:27Z | - |
dc.date.issued | 2019-01 | - |
dc.identifier.citation | IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, v. 31, NO 1, Page. 3-16 | en_US |
dc.identifier.issn | 1041-4347 | - |
dc.identifier.issn | 1558-2191 | - |
dc.identifier.uri | https://ieeexplore.ieee.org/document/7913668 | - |
dc.identifier.uri | https://repository.hanyang.ac.kr/handle/20.500.11754/132980 | - |
dc.description.abstract | We develop a novel framework, named as iota-injection, to address the sparsity problem of recommender systems. By carefully injecting low values to a selected set of unrated user-item pairs in a user-item matrix, we demonstrate that top-N recommendation accuracies of various collaborative filtering (CF) techniques can be significantly and consistently improved. We first adopt the notion of pre-use preferences of users toward a vast amount of unrated items. Using this notion, we identify uninteresting items that have not been rated yet but are likely to receive low ratings from users, and selectively impute them as low values. As our proposed approach is method-agnostic, it can be easily applied to a variety of CF algorithms. Through comprehensive experiments with three real-life datasets (e.g., Movielens, Ciao, and Watcha), we demonstrate that our solution consistently and universally enhances the accuracies of existing CF algorithms (e.g., item-based CF, SVD-based CF, and SVD++) by 2.5 to 5 times on average. Furthermore, our solution improves the running time of those CF methods by 1.2 to 2.3 times when its setting produces the best accuracy. | en_US |
dc.description.sponsorship | This research was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIP) (NRF-2017R1A2B3004581), the Ministry of Science, ICT and Future Planning (MSIP), Korea, under the Information Technology Research Center (ITRC) support program (IITP-2017-2013-0-00881), and two awards of NSF CNS-1422215 and Samsung 2015 GRO-175998. Sang-Wook Kim is the corresponding author. | en_US |
dc.language.iso | en | en_US |
dc.publisher | IEEE COMPUTER SOC | en_US |
dc.subject | Recommender systems | en_US |
dc.subject | collaborative filtering | en_US |
dc.subject | data sparsity | en_US |
dc.subject | uninteresting items | en_US |
dc.subject | pre-use preference | en_US |
dc.subject | post-use preference | en_US |
dc.title | l-Injection: Toward Effective Collaborative Filtering Using Uninteresting Items | en_US |
dc.type | Article | en_US |
dc.relation.no | 1 | - |
dc.relation.volume | 31 | - |
dc.identifier.doi | 10.1109/TKDE.2017.2698461 | - |
dc.relation.page | 3-16 | - |
dc.relation.journal | IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING | - |
dc.contributor.googleauthor | Lee, Jongwuk | - |
dc.contributor.googleauthor | Hwang, Won-Seok | - |
dc.contributor.googleauthor | Parc, Juan | - |
dc.contributor.googleauthor | Lee, Youngnam | - |
dc.contributor.googleauthor | Kim, Sang-Wook | - |
dc.contributor.googleauthor | Lee, Dongwon | - |
dc.relation.code | 2019000170 | - |
dc.sector.campus | S | - |
dc.sector.daehak | COLLEGE OF ENGINEERING[S] | - |
dc.sector.department | DEPARTMENT OF COMPUTER SCIENCE | - |
dc.identifier.pid | wook | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.