Print Email Facebook Twitter MRLR Title MRLR: Multi-level representation learning for personalized ranking in recommendation Author Sun, Zhu (Nanyang Technological University) Yang, J. (TU Delft Web Information Systems) Zhang, Jie (Nanyang Technological University) Bozzon, A. (TU Delft Web Information Systems) Chen, Yu (Nanyang Technological University) Xu, Chi (Singapore Institute of Manufacturing Technology) Contributor Sierra, C. (editor) Date 2017 Abstract Representation learning (RL) has recently proven to be effective in capturing local item relationships by modeling item co-occurrence in individual user's interaction record. However, the value of RL for recommendation has not reached the full potential due to two major drawbacks: 1) recommendation is modeled as a rating prediction problem but should essentially be a personalized ranking one; 2) multi-level organizations of items are neglected for fine-grained item relationships. We design a unified Bayesian framework MRLR to learn user and item embeddings from a multi-level item organization, thus benefiting from RL as well as achieving the goal of personalized ranking. Extensive validation on real-world datasets shows that MRLR consistently outperforms state-of-the-art algorithms. To reference this document use: http://resolver.tudelft.nl/uuid:7db2d2d5-0ab5-4e63-8943-6431818a7fda DOI https://doi.org/10.24963/ijcai.2017/391 Publisher International Joint Conferences on Artificial Intelligence (IJCAI) ISBN 9780999241103 Source 26th International Joint Conference on Artificial Intelligence, IJCAI 2017 Event IJCAI 2017, 2017-08-19 → 2017-08-25, Melbourne, Australia Part of collection Institutional Repository Document type conference paper Rights © 2017 Zhu Sun, J. Yang, Jie Zhang, A. Bozzon, Yu Chen, Chi Xu Files PDF 0391.pdf 333.39 KB Close viewer /islandora/object/uuid:7db2d2d5-0ab5-4e63-8943-6431818a7fda/datastream/OBJ/view