{"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/discriminative-gaifman-models","title":"Discriminative Gaifman Models","arxiv_id":"1610.09369","date":"2016-10-28","proceeding":"NeurIPS 2016 12","authors":["Mathias Niepert"],"abstract":"We present discriminative Gaifman models, a novel family of relational\nmachine learning models. Gaifman models learn feature representations bottom up\nfrom representations of locally connected and bounded-size regions of knowledge\nbases (KBs). Considering local and bounded-size neighborhoods of knowledge\nbases renders logical inference and learning tractable, mitigates the problem\nof overfitting, and facilitates weight sharing. Gaifman models sample\nneighborhoods of knowledge bases so as to make the learned relational models\nmore robust to missing objects and relations which is a common situation in\nopen-world KBs. We present the core ideas of Gaifman models and apply them to\nlarge-scale relational learning problems. We also discuss the ways in which\nGaifman models relate to some existing relational machine learning approaches.","url_abs":"http://arxiv.org/abs/1610.09369v1","url_pdf":"http://arxiv.org/pdf/1610.09369v1.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":[],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"link-prediction","task_name":"Link Prediction"},{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/link-prediction-on-wn18","task":"Link Prediction","dataset":"WN18","model":"Gaifman","rank_in_archive_order":28,"of":37,"metrics":{"Hits@1":"0.761","Hits@10":"0.939","MR":"352"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}