{"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/lifted-relational-neural-networks","title":"Lifted Relational Neural Networks","arxiv_id":"1508.05128","date":"2015-08-20","proceeding":null,"authors":["Gustav Sourek","Vojtech Aschenbrenner","Filip Zelezny","Ondrej Kuzelka"],"abstract":"We propose a method combining relational-logic representations with neural\nnetwork learning. A general lifted architecture, possibly reflecting some\nbackground domain knowledge, is described through relational rules which may be\nhandcrafted or learned. The relational rule-set serves as a template for\nunfolding possibly deep neural networks whose structures also reflect the\nstructures of given training or testing relational examples. Different networks\ncorresponding to different examples share their weights, which co-evolve during\ntraining by stochastic gradient descent algorithm. The framework allows for\nhierarchical relational modeling constructs and learning of latent relational\nconcepts through shared hidden layers weights corresponding to the rules.\nDiscovery of notable relational concepts and experiments on 78 relational\nlearning benchmarks demonstrate favorable performance of the method.","url_abs":"http://arxiv.org/abs/1508.05128v2","url_pdf":"http://arxiv.org/pdf/1508.05128v2.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":"lifted-relational-neural-networks","repo_url":"https://github.com/GustikS/NeuraLogic","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"relational-reasoning","task_name":"Relational Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1508.05128","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}