{"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/on-inductive-abilities-of-latent-factor","title":"On Inductive Abilities of Latent Factor Models for Relational Learning","arxiv_id":"1709.05666","date":"2017-09-17","proceeding":null,"authors":["Théo Trouillon","Éric Gaussier","Christopher R. Dance","Guillaume Bouchard"],"abstract":"Latent factor models are increasingly popular for modeling multi-relational\nknowledge graphs. By their vectorial nature, it is not only hard to interpret\nwhy this class of models works so well, but also to understand where they fail\nand how they might be improved. We conduct an experimental survey of\nstate-of-the-art models, not towards a purely comparative end, but as a means\nto get insight about their inductive abilities. To assess the strengths and\nweaknesses of each model, we create simple tasks that exhibit first, atomic\nproperties of binary relations, and then, common inter-relational inference\nthrough synthetic genealogies. Based on these experimental results, we propose\nnew research directions to improve on existing models.","url_abs":"http://arxiv.org/abs/1709.05666v1","url_pdf":"http://arxiv.org/pdf/1709.05666v1.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":"on-inductive-abilities-of-latent-factor","repo_url":"https://github.com/ttrouill/induction_experiments","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"knowledge-graphs","task_name":"Knowledge Graphs"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1709.05666","atlas_url":"https://app.syntology.ai/?focus=1709.05666","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}