{"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/kernelized-synaptic-weight-matrices","title":"Kernelized Synaptic Weight Matrices","arxiv_id":null,"date":"2018-07-01","proceeding":"ICML 2018 7","authors":["Lorenz Muller","Julien Martel","Giacomo Indiveri"],"abstract":"\n    In this paper we introduce a novel neural network architecture, in which weight matrices are re-parametrized in terms of low-dimensional vectors, interacting through kernel functions. A layer of our network can be interpreted as introducing a (potentially infinitely wide) linear layer between input and output. We describe the theory underpinning this model and validate it with concrete examples, exploring how it can be used to impose structure on neural networks in diverse applications ranging from data visualization to recommender systems. We achieve state-of-the-art performance in a collaborative filtering task (MovieLens).\n  ","url_abs":"https://icml.cc/Conferences/2018/Schedule?showEvent=2141","url_pdf":"http://proceedings.mlr.press/v80/muller18a/muller18a.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":"kernelized-synaptic-weight-matrices","repo_url":"https://github.com/RD211/kernelNet_recommender","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null},{"paper_slug":"kernelized-synaptic-weight-matrices","repo_url":"https://github.com/lorenzMuller/kernelNet_MovieLens","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"tf","reach":null}],"tasks":[{"task_slug":"collaborative-filtering","task_name":"Collaborative Filtering"},{"task_slug":"data-visualization","task_name":"Data Visualization"},{"task_slug":"recommendation-systems","task_name":"Recommendation Systems"}],"methods":[{"method_slug":"linear-layer","method_name":"Linear Layer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/collaborative-filtering-on-movielens-10m","task":"Recommendation Systems","dataset":"MovieLens 10M","model":"Sparse FC","rank_in_archive_order":5,"of":17,"metrics":{"RMSE":"0.769"},"uses_additional_data":false},{"leaderboard":"/sota/collaborative-filtering-on-movielens-1m","task":"Recommendation Systems","dataset":"MovieLens 1M","model":"Sparse FC","rank_in_archive_order":2,"of":31,"metrics":{"RMSE":"0.824"},"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}