{"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/learning-explanatory-rules-from-noisy-data","title":"Learning Explanatory Rules from Noisy Data","arxiv_id":"1711.04574","date":"2017-11-13","proceeding":null,"authors":["Richard Evans","Edward Grefenstette"],"abstract":"Artificial Neural Networks are powerful function approximators capable of\nmodelling solutions to a wide variety of problems, both supervised and\nunsupervised. As their size and expressivity increases, so too does the\nvariance of the model, yielding a nearly ubiquitous overfitting problem.\nAlthough mitigated by a variety of model regularisation methods, the common\ncure is to seek large amounts of training data---which is not necessarily\neasily obtained---that sufficiently approximates the data distribution of the\ndomain we wish to test on. In contrast, logic programming methods such as\nInductive Logic Programming offer an extremely data-efficient process by which\nmodels can be trained to reason on symbolic domains. However, these methods are\nunable to deal with the variety of domains neural networks can be applied to:\nthey are not robust to noise in or mislabelling of inputs, and perhaps more\nimportantly, cannot be applied to non-symbolic domains where the data is\nambiguous, such as operating on raw pixels. In this paper, we propose a\nDifferentiable Inductive Logic framework, which can not only solve tasks which\ntraditional ILP systems are suited for, but shows a robustness to noise and\nerror in the training data which ILP cannot cope with. Furthermore, as it is\ntrained by backpropagation against a likelihood objective, it can be hybridised\nby connecting it with neural networks over ambiguous data in order to be\napplied to domains which ILP cannot address, while providing data efficiency\nand generalisation beyond what neural networks on their own can achieve.","url_abs":"http://arxiv.org/abs/1711.04574v2","url_pdf":"http://arxiv.org/pdf/1711.04574v2.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":"learning-explanatory-rules-from-noisy-data","repo_url":"https://github.com/ai-systems/DILP-Core","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"learning-explanatory-rules-from-noisy-data","repo_url":"https://github.com/crunchiness/lernd","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"GPL-3.0"}},{"paper_slug":"learning-explanatory-rules-from-noisy-data","repo_url":"https://github.com/stomir/dilp2","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"inductive-logic-programming","task_name":"Inductive logic programming"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1711.04574","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1711.04574"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/crunchiness/lernd","reach":{"status":"ok","spdx":"GPL-3.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/stomir/dilp2","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/ai-systems/DILP-Core","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_draft_wrong":1},"by_repo_kind":{"listed":{"samples":3,"ran":3,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":3,"samples":[{"code_sha256_prefix":"c9240446d10d4815","entry":"conjunction2_prod","repo":"stomir/dilp2","repo_kind":"listed","path":"dilp.py","file_url":"https://github.com/stomir/dilp2/blob/HEAD/dilp.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c9240446d10d4815"}},{"code_sha256_prefix":"c42b4369848f968e","entry":"disjunction2_prod","repo":"stomir/dilp2","repo_kind":"listed","path":"dilp.py","file_url":"https://github.com/stomir/dilp2/blob/HEAD/dilp.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c42b4369848f968e"}},{"code_sha256_prefix":"91dcd2ca613f6a58","entry":"disjunction_dim_prod","repo":"stomir/dilp2","repo_kind":"listed","path":"dilp.py","file_url":"https://github.com/stomir/dilp2/blob/HEAD/dilp.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"91dcd2ca613f6a58"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}