{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T12:51:21Z","timestamp":1769518281945,"version":"3.49.0"},"reference-count":58,"publisher":"Association for Computing Machinery (ACM)","issue":"1","license":[{"start":{"date-parts":[[2019,1,9]],"date-time":"2019-01-09T00:00:00Z","timestamp":1546992000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100003848","name":"Industrial Technology Research Institute","doi-asserted-by":"crossref","award":["ITRI 107-W1-21A2"],"award-info":[{"award-number":["ITRI 107-W1-21A2"]}],"id":[{"id":"10.13039\/501100003848","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Ministry of Science and Technology","award":["MOST 107-2221-E-008-077-MY3"],"award-info":[{"award-number":["MOST 107-2221-E-008-077-MY3"]}]},{"name":"CHANGING.AI"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2019,2,28]]},"abstract":"<jats:p>\n            Matrix factorization (MF) and its extended methodologies have been studied extensively in the community of recommender systems in the last decade. Essentially, MF attempts to search for low-ranked matrices that can (1) best approximate the known rating scores, and (2) maintain low Frobenius norm for the low-ranked matrices to prevent overfitting. Since the two objectives conflict with each other, the common practice is to assign the relative importance weights as the hyper-parameters to these objectives. The two low-ranked matrices returned by MF are often interpreted as the latent factors of a user and the latent factors of an item that would affect the rating of the user on the item. As a result, it is typical that, in the loss function, we assign a regularization weight \u03bb\n            <jats:sub>\n              <jats:italic>p<\/jats:italic>\n            <\/jats:sub>\n            on the norms of the latent factors for all users, and another regularization weight \u03bb\n            <jats:sub>\n              <jats:italic>q<\/jats:italic>\n            <\/jats:sub>\n            on the norms of the latent factors for all the items. We argue that such a methodology probably over-simplifies the scenario. Alternatively, we probably should assign lower constraints to the latent factors associated with the items or users that reveal more information, and set higher constraints to the others. In this article, we systematically study this topic. We found that such a simple technique can improve the prediction results of the MF-based approaches based on several public datasets. Specifically, we applied the proposed methodology on three baseline models -- SVD, SVD++, and the NMF models. We found that this technique improves the prediction accuracy for all these baseline models. Perhaps more importantly, this technique better predicts the ratings on the long-tail items, i.e., the items that were rated\/viewed\/purchased by few users. This suggests that this approach may partially remedy the cold-start issue. The proposed method is very general and can be easily applied on various recommendation models, such as Factorization Machines, Field-aware Factorization Machines, Factorizing Personalized Markov Chains, Prod2Vec, Behavior2Vec, and so on. We release the code for reproducibility. We implemented a Python package that integrates the proposed regularization technique with the SVD, SVD++, and the NMF model. The package can be accessed at https:\/\/github.com\/ncu-dart\/rdf.\n          <\/jats:p>","DOI":"10.1145\/3285954","type":"journal-article","created":{"date-parts":[[2019,1,9]],"date-time":"2019-01-09T18:36:36Z","timestamp":1547058996000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":21,"title":["Differentiating Regularization Weights -- A Simple Mechanism to Alleviate Cold Start in Recommender Systems"],"prefix":"10.1145","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5137-4449","authenticated-orcid":false,"given":"Hung-Hsuan","family":"Chen","sequence":"first","affiliation":[{"name":"National Central University, Zhongli District, Taoyuan City, Taiwan (R.O.C.)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pu","family":"Chen","sequence":"additional","affiliation":[{"name":"National Central University, Zhongli District, Taoyuan City, Taiwan (R.O.C.)"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2019,1,9]]},"reference":[{"key":"e_1_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11257-012-9131-2"},{"key":"e_1_2_1_2_1","unstructured":"Lukas Brozovsky and Vaclav Petricek. 2007. Recommender system for online dating service. arXiv: cs\/0703042.  Lukas Brozovsky and Vaclav Petricek. 2007. Recommender system for online dating service. arXiv: cs\/0703042."},{"key":"e_1_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.49.11.1580.20580"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104344"},{"key":"e_1_2_1_5_1","unstructured":"Rich Caruana Steve Lawrence and C. Lee Giles. 2001. Overfitting in neural nets: Backpropagation conjugate gradient and early stopping. In Advances in Neural Information Processing Systems. 402--408.   Rich Caruana Steve Lawrence and C. Lee Giles. 2001. Overfitting in neural nets: Backpropagation conjugate gradient and early stopping. In Advances in Neural Information Processing Systems. 402--408."},{"key":"e_1_2_1_6_1","unstructured":"Hung-Hsuan Chen. 2017. Weighted-SVD: Matrix factorization with weights on the latent factors. arXiv:1710.00482.  Hung-Hsuan Chen. 2017. Weighted-SVD: Matrix factorization with weights on the latent factors. arXiv:1710.00482."},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3184454"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3137597.3137601"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/2776894"},{"key":"e_1_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/1998076.1998121"},{"key":"e_1_2_1_11_1","unstructured":"Hung-Hsuan Chen II Ororbia G. Alexander and C. Lee Giles. 2015. ExpertSeer: A keyphrase based expert recommender for digital libraries. arXiv:1511.02058.  Hung-Hsuan Chen II Ororbia G. Alexander and C. Lee Giles. 2015. ExpertSeer: A keyphrase based expert recommender for digital libraries. arXiv:1511.02058."},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/72.788648"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1214\/ss\/1177013815"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1080\/01972240490507974"},{"key":"e_1_2_1_15_1","volume-title":"The elements of Statistical Learning","author":"Friedman Jerome"},{"key":"e_1_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020426"},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/1594139.1594155"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788627"},{"key":"e_1_2_1_19_1","volume-title":"Proceedings of the 23rd International Joint Conference on Artificial Intelligence (IJCAI\u201913)","author":"Guo G."},{"key":"e_1_2_1_20_1","unstructured":"Greg Hamerly and Charles Elkan. 2004. Learning the k in k-means. In Advances in Neural Information Processing Systems. 281--288.   Greg Hamerly and Charles Elkan. 2004. Learning the k in k-means. In Advances in Neural Information Processing Systems. 281--288."},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2827872"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/2872427.2883037"},{"key":"e_1_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052569"},{"key":"e_1_2_1_24_1","unstructured":"Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv:1511.06939.  Bal\u00e1zs Hidasi Alexandros Karatzoglou Linas Baltrunas and Domonkos Tikk. 2015. Session-based recommendations with recurrent neural networks. arXiv:1511.06939."},{"key":"e_1_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.2307\/1271436"},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1145\/2959100.2959134"},{"key":"e_1_2_1_27_1","volume-title":"Proceedings of the 14th International Joint Conference on Artificial Intelligence","volume":"2","author":"Kohavi Ron","year":"1995"},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2009.263"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109929"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2365952.2365977"},{"key":"e_1_2_1_31_1","unstructured":"Omer Levy and Yoav Goldberg. 2014. Neural word embedding as implicit matrix factorization. In Advances in Neural Information Processing Systems. 2177--2185.   Omer Levy and Yoav Goldberg. 2014. Neural word embedding as implicit matrix factorization. In Advances in Neural Information Processing Systems. 2177--2185."},{"key":"e_1_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772758"},{"key":"e_1_2_1_33_1","unstructured":"Cheng-You Lien Guo-Jhen Bai Ting-Rui Chen and Hung-Hsuan Chen. 2017. Predicting user\u2019s online shopping tendency during shopping holidays. (2017).  Cheng-You Lien Guo-Jhen Bai Ting-Rui Chen and Hung-Hsuan Chen. 2017. Predicting user\u2019s online shopping tendency during shopping holidays. (2017)."},{"key":"e_1_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2013.09.005"},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3109859.3109886"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639717"},{"key":"e_1_2_1_37_1","volume-title":"Proceedings of the 23rd Conference on Uncertainty in Artificial Intelligence (UAI\u201907)","author":"Marlin Benjamin M.","year":"2007"},{"key":"e_1_2_1_38_1","first-page":"31","article-title":"Trustlet, open research on trust metrics","volume":"9","author":"Massa Paolo","year":"2001","journal-title":"Scalable Computing: Practice and Experience"},{"key":"e_1_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766462.2767755"},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.5555\/2034117.2034146"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2488388.2488467"},{"key":"e_1_2_1_42_1","volume-title":"Proceedings of the 15th International Conference on Machine Learning (ICML\u201998)","author":"Ng Andrew Y.","year":"1998"},{"key":"e_1_2_1_43_1","volume-title":"Individuals and information overload in organizations: Is more necessarily better?Academy of Management Journal 23, 4","author":"O\u2019reilly Charles A.","year":"1980"},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/1639714.1639720"},{"key":"e_1_2_1_45_1","volume-title":"Cooper","author":"Perrone Michael P.","year":"1995"},{"key":"e_1_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.83.066114"},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/502716.502737"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1540276.1540302"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772773"},{"key":"e_1_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564421"},{"key":"e_1_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1145\/2433396.2433451"},{"key":"e_1_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"e_1_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1145\/3018661.3018689"},{"key":"e_1_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.5555\/3172077.3172336"},{"key":"e_1_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/2009916.2009961"},{"key":"e_1_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3285954","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3285954","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T00:44:14Z","timestamp":1750207454000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3285954"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,1,9]]},"references-count":58,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2019,2,28]]}},"alternative-id":["10.1145\/3285954"],"URL":"https:\/\/doi.org\/10.1145\/3285954","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"value":"1556-4681","type":"print"},{"value":"1556-472X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,1,9]]},"assertion":[{"value":"2018-06-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2018-10-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-01-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}