{"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/a-semantic-loss-function-for-deep-learning","title":"A Semantic Loss Function for Deep Learning with Symbolic Knowledge","arxiv_id":"1711.11157","date":"2017-11-29","proceeding":"ICML 2018 7","authors":["Jingyi Xu","Zilu Zhang","Tal Friedman","Yitao Liang","Guy Van Den Broeck"],"abstract":"This paper develops a novel methodology for using symbolic knowledge in deep\nlearning. From first principles, we derive a semantic loss function that\nbridges between neural output vectors and logical constraints. This loss\nfunction captures how close the neural network is to satisfying the constraints\non its output. An experimental evaluation shows that it effectively guides the\nlearner to achieve (near-)state-of-the-art results on semi-supervised\nmulti-class classification. Moreover, it significantly increases the ability of\nthe neural network to predict structured objects, such as rankings and paths.\nThese discrete concepts are tremendously difficult to learn, and benefit from a\ntight integration of deep learning and symbolic reasoning methods.","url_abs":"http://arxiv.org/abs/1711.11157v2","url_pdf":"http://arxiv.org/pdf/1711.11157v2.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":"a-semantic-loss-function-for-deep-learning","repo_url":"https://github.com/UCLA-StarAI/Semantic-Loss","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"tf","reach":{"status":"unanswered"}}],"tasks":[{"task_slug":"deep-learning","task_name":"Deep Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"multi-class-classification","task_name":"Multi-class Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.11157","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}