{"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-compositional-rules-via-neural","title":"Learning Compositional Rules via Neural Program Synthesis","arxiv_id":"2003.05562","date":"2020-03-12","proceeding":"NeurIPS 2020 12","authors":["Maxwell I. Nye","Armando Solar-Lezama","Joshua B. Tenenbaum","Brenden M. Lake"],"abstract":"Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and combining these rules to form compositional rule-based systems. Current neural architectures, on the other hand, often fail to generalize in a compositional manner, especially when evaluated in ways that vary systematically from training. In this work, we present a neuro-symbolic model which learns entire rule systems from a small set of examples. Instead of directly predicting outputs from inputs, we train our model to induce the explicit system of rules governing a set of previously seen examples, drawing upon techniques from the neural program synthesis literature. Our rule-synthesis approach outperforms neural meta-learning techniques in three domains: an artificial instruction-learning domain used to evaluate human learning, the SCAN challenge datasets, and learning rule-based translations of number words into integers for a wide range of human languages.","url_abs":"https://arxiv.org/abs/2003.05562v2","url_pdf":"https://arxiv.org/pdf/2003.05562v2.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-compositional-rules-via-neural","repo_url":"https://github.com/mtensor/rulesynthesis","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"program-synthesis","task_name":"Program Synthesis"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2003.05562","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.05562"}},"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/mtensor/rulesynthesis","reach":null}],"summary":{"ran":1,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":5,"ran":4,"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":5,"samples":[{"code_sha256_prefix":"4de24e46c8209aaf","entry":"PositionalEncoder","repo":"mtensor/rulesynthesis","repo_kind":"official","path":"batched_synth_net.py","file_url":"https://github.com/mtensor/rulesynthesis/blob/HEAD/batched_synth_net.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4de24e46c8209aaf"}},{"code_sha256_prefix":"324537dd7c7ee111","entry":"asMinutes","repo":"mtensor/rulesynthesis","repo_kind":"official","path":"train_metanet_attn.py","file_url":"https://github.com/mtensor/rulesynthesis/blob/HEAD/train_metanet_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"324537dd7c7ee111"}},{"code_sha256_prefix":"39b0d55da5e13f32","entry":"make_hashable","repo":"mtensor/rulesynthesis","repo_kind":"official","path":"train_metanet_attn.py","file_url":"https://github.com/mtensor/rulesynthesis/blob/HEAD/train_metanet_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"39b0d55da5e13f32"}},{"code_sha256_prefix":"c0a5b7ee10788222","entry":"timeSince","repo":"mtensor/rulesynthesis","repo_kind":"official","path":"train_metanet_attn.py","file_url":"https://github.com/mtensor/rulesynthesis/blob/HEAD/train_metanet_attn.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"c0a5b7ee10788222"}},{"code_sha256_prefix":"018a3d57a65e2241","entry":"BatchedRuleSynthEncoderRNN","repo":"mtensor/rulesynthesis","repo_kind":"official","path":"batched_synth_net.py","file_url":"https://github.com/mtensor/rulesynthesis/blob/HEAD/batched_synth_net.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"018a3d57a65e2241"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}