{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/glocal-k-global-and-local-kernels-for","title":"GLocal-K: Global and Local Kernels for Recommender Systems","arxiv_id":"2108.12184","date":"2021-08-27","proceeding":null,"authors":["Soyeon Caren Han","Taejun Lim","Siqu Long","Bernd Burgstaller","Josiah Poon"],"abstract":"Recommender systems typically operate on high-dimensional sparse user-item matrices. Matrix completion is a very challenging task to predict one's interest based on millions of other users having each seen a small subset of thousands of items. We propose a Global-Local Kernel-based matrix completion framework, named GLocal-K, that aims to generalise and represent a high-dimensional sparse user-item matrix entry into a low dimensional space with a small number of important features. Our GLocal-K can be divided into two major stages. First, we pre-train an auto encoder with the local kernelised weight matrix, which transforms the data from one space into the feature space by using a 2d-RBF kernel. Then, the pre-trained auto encoder is fine-tuned with the rating matrix, produced by a convolution-based global kernel, which captures the characteristics of each item. We apply our GLocal-K model under the extreme low-resource setting, which includes only a user-item rating matrix, with no side information. Our model outperforms the state-of-the-art baselines on three collaborative filtering benchmarks: ML-100K, ML-1M, and Douban.","url_abs":"https://arxiv.org/abs/2108.12184v1","url_pdf":"https://arxiv.org/pdf/2108.12184v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"glocal-k-global-and-local-kernels-for","repo_url":"https://github.com/usydnlp/Glocal_K","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"glocal-k-global-and-local-kernels-for","repo_url":"https://github.com/fleanend/NeuralRecommender","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"glocal-k-global-and-local-kernels-for","repo_url":"https://github.com/fleanend/TorchGlocalK","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"matrix-completion","task_name":"Matrix Completion"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/recommendation-systems-on-douban-monti","task":"Recommendation Systems","dataset":"Douban Monti","model":"GLocal-K","rank_in_archive_order":1,"of":8,"metrics":{"RMSE":"0.7208"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-movielens-100k","task":"Recommendation Systems","dataset":"MovieLens 100K","model":"GLocal-K","rank_in_archive_order":3,"of":18,"metrics":{"RMSE (u1 Splits)":"0.8889"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-movielens-1m","task":"Recommendation Systems","dataset":"MovieLens 1M","model":"GLocal-K","rank_in_archive_order":1,"of":31,"metrics":{"RMSE":"0.8227"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}