How Important is Periodic Model Update in Recommender Systems?
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Lee, H.[Lee, Hyunsung] | - |
dc.contributor.author | Lee, D.[Lee, Dongjun] | - |
dc.contributor.author | Yoo, S.[Yoo, Sungwook] | - |
dc.contributor.author | Kim, J.[Kim, Jaekwang] | - |
dc.date.accessioned | 2023-09-12T00:46:24Z | - |
dc.date.available | 2023-09-12T00:46:24Z | - |
dc.date.created | 2023-09-12 | - |
dc.date.issued | 2023-07-19 | - |
dc.identifier.issn | 0000-0000 | - |
dc.identifier.uri | https://scholarworks.bwise.kr/skku/handle/2021.sw.skku/108131 | - |
dc.description.abstract | In real-world recommender model deployments, the models are typically retrained and deployed repeatedly. It is the rule-of-thumb to periodically retrain recommender models to capture up-to-date user behavior and item trends. However, the harm caused by delayed model updates has not been investigated extensively yet. in this perspective paper, we formulate the delayed model update problem and quantitatively demonstrate the delayed model update actually harms the model performance by increasing the number of cold users and cold items increase and decreasing overall model performances. These effects vary across different domains having different characteristics. Upon these findings, we further argue that although the delayed model update has negative effects on online recommender model deployment, yet it has not gathered enough attention from research communities. We argue our verification of the relationship between the model update cycle and model performance calls for further research such as faster model training, and more efficient data pipelines to keep the model more up-to-date with the latest user behaviors and item trends. © 2023 Copyright held by the owner/author(s). Publication rights licensed to ACM. | - |
dc.language | 영어 | - |
dc.language.iso | en | - |
dc.publisher | Association for Computing Machinery, Inc | - |
dc.title | How Important is Periodic Model Update in Recommender Systems? | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | Lee, D.[Lee, Dongjun] | - |
dc.contributor.affiliatedAuthor | Kim, J.[Kim, Jaekwang] | - |
dc.identifier.doi | 10.1145/3539618.3591934 | - |
dc.identifier.scopusid | 2-s2.0-85168659983 | - |
dc.identifier.bibliographicCitation | SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp.2661 - 2668 | - |
dc.relation.isPartOf | SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval | - |
dc.citation.title | SIGIR 2023 - Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval | - |
dc.citation.startPage | 2661 | - |
dc.citation.endPage | 2668 | - |
dc.type.rims | ART | - |
dc.type.docType | Conference paper | - |
dc.description.journalClass | 1 | - |
dc.description.journalRegisteredClass | scopus | - |
dc.subject.keywordAuthor | Delayed Model Update | - |
dc.subject.keywordAuthor | Model Retraining | - |
dc.subject.keywordAuthor | Recommender Systems | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(03063) 25-2, SUNGKYUNKWAN-RO, JONGNO-GU, SEOUL, KOREAsamsunglib@skku.edu
COPYRIGHT © 2021 SUNGKYUNKWAN UNIVERSITY ALL RIGHTS RESERVED.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.