{"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/tensorlog-a-differentiable-deductive-database","title":"TensorLog: A Differentiable Deductive Database","arxiv_id":"1605.06523","date":"2016-05-20","proceeding":null,"authors":["William W. Cohen"],"abstract":"Large knowledge bases (KBs) are useful in many tasks, but it is unclear how\nto integrate this sort of knowledge into \"deep\" gradient-based learning\nsystems. To address this problem, we describe a probabilistic deductive\ndatabase, called TensorLog, in which reasoning uses a differentiable process.\nIn TensorLog, each clause in a logical theory is first converted into certain\ntype of factor graph. Then, for each type of query to the factor graph, the\nmessage-passing steps required to perform belief propagation (BP) are\n\"unrolled\" into a function, which is differentiable. We show that these\nfunctions can be composed recursively to perform inference in non-trivial\nlogical theories containing multiple interrelated clauses and predicates. Both\ncompilation and inference in TensorLog are efficient: compilation is linear in\ntheory size and proof depth, and inference is linear in database size and the\nnumber of message-passing steps used in BP. We also present experimental\nresults with TensorLog and discuss its relationship to other first-order\nprobabilistic logics.","url_abs":"http://arxiv.org/abs/1605.06523v2","url_pdf":"http://arxiv.org/pdf/1605.06523v2.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":"tensorlog-a-differentiable-deductive-database","repo_url":"https://github.com/logic-reasoning/Paper-Reading","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"unanswered"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1605.06523","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}