{"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/slice-based-learning-a-programming-model-for","title":"Slice-based Learning: A Programming Model for Residual Learning in Critical Data Slices","arxiv_id":"1909.06349","date":"2019-09-13","proceeding":"NeurIPS 2019 12","authors":["Vincent S. Chen","Sen Wu","Zhenzhen Weng","Alexander Ratner","Christopher Ré"],"abstract":"In real-world machine learning applications, data subsets correspond to especially critical outcomes: vulnerable cyclist detections are safety-critical in an autonomous driving task, and \"question\" sentences might be important to a dialogue agent's language understanding for product purposes. While machine learning models can achieve high quality performance on coarse-grained metrics like F1-score and overall accuracy, they may underperform on critical subsets---we define these as slices, the key abstraction in our approach. To address slice-level performance, practitioners often train separate \"expert\" models on slice subsets or use multi-task hard parameter sharing. We propose Slice-based Learning, a new programming model in which the slicing function (SF), a programming interface, specifies critical data subsets for which the model should commit additional capacity. Any model can leverage SFs to learn slice expert representations, which are combined with an attention mechanism to make slice-aware predictions. We show that our approach maintains a parameter-efficient representation while improving over baselines by up to 19.0 F1 on slices and 4.6 F1 overall on datasets spanning language understanding (e.g. SuperGLUE), computer vision, and production-scale industrial systems.","url_abs":"https://arxiv.org/abs/1909.06349v2","url_pdf":"https://arxiv.org/pdf/1909.06349v2.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":"slice-based-learning-a-programming-model-for","repo_url":"https://github.com/snorkel-team/snorkel-tutorials","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"slice-based-learning-a-programming-model-for","repo_url":"https://github.com/Guzpenha/slice_based_learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1909.06349","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1909.06349"}},"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/Guzpenha/slice_based_learning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/snorkel-team/snorkel-tutorials","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":10},"by_repo_kind":{"official":{"samples":10,"ran":0,"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":0,"samples":[{"code_sha256_prefix":"1b33659fda6fb25d","entry":"bilstm","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"spouse/tf_model.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/spouse/tf_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1b33659fda6fb25d"}},{"code_sha256_prefix":"ffa6ecdde4fa2112","entry":"crop_img_arr","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"visual_relation/model.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/visual_relation/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ffa6ecdde4fa2112"}},{"code_sha256_prefix":"f01e0cb2f41ce3de","entry":"get_feature_arrays","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"spouse/tf_model.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/spouse/tf_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f01e0cb2f41ce3de"}},{"code_sha256_prefix":"61451811170bbe5c","entry":"get_model","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"spouse/tf_model.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/spouse/tf_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"61451811170bbe5c"}},{"code_sha256_prefix":"3f5e64c950b28d95","entry":"load_celebrity_knowledge_base","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"drybell/drybell_lfs.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/drybell/drybell_lfs.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f5e64c950b28d95"}},{"code_sha256_prefix":"4158af3b070ad02e","entry":"make_circle_dataset","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"multitask/utils.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/multitask/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4158af3b070ad02e"}},{"code_sha256_prefix":"396134a8f97c18ce","entry":"make_inv_circle_dataset","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"multitask/utils.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/multitask/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"396134a8f97c18ce"}},{"code_sha256_prefix":"a6a538bb4423725c","entry":"make_square_dataset","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"multitask/utils.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/multitask/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a6a538bb4423725c"}},{"code_sha256_prefix":"374f0cdaed9f408d","entry":"union","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"visual_relation/model.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/visual_relation/model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"374f0cdaed9f408d"}},{"code_sha256_prefix":"cd95474a04a1610b","entry":"worker_lf","repo":"snorkel-team/snorkel-tutorials","repo_kind":"official","path":"crowdsourcing/crowdsourcing_tutorial.py","file_url":"https://github.com/snorkel-team/snorkel-tutorials/blob/HEAD/crowdsourcing/crowdsourcing_tutorial.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"cd95474a04a1610b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}