{"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-to-defer-to-a-population-a-meta","title":"Learning to Defer to a Population: A Meta-Learning Approach","arxiv_id":"2403.02683","date":"2024-03-05","proceeding":null,"authors":["Dharmesh Tailor","Aditya Patra","Rajeev Verma","Putra Manggala","Eric Nalisnick"],"abstract":"The learning to defer (L2D) framework allows autonomous systems to be safe and robust by allocating difficult decisions to a human expert. All existing work on L2D assumes that each expert is well-identified, and if any expert were to change, the system should be re-trained. In this work, we alleviate this constraint, formulating an L2D system that can cope with never-before-seen experts at test-time. We accomplish this by using meta-learning, considering both optimization- and model-based variants. Given a small context set to characterize the currently available expert, our framework can quickly adapt its deferral policy. For the model-based approach, we employ an attention mechanism that is able to look for points in the context set that are similar to a given test point, leading to an even more precise assessment of the expert's abilities. In the experiments, we validate our methods on image recognition, traffic sign detection, and skin lesion diagnosis benchmarks.","url_abs":"https://arxiv.org/abs/2403.02683v2","url_pdf":"https://arxiv.org/pdf/2403.02683v2.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-to-defer-to-a-population-a-meta","repo_url":"https://github.com/dvtailor/meta-l2d","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"traffic-sign-detection","task_name":"Traffic Sign Detection"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2403.02683","atlas_url":"https://app.syntology.ai/?focus=2403.02683","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2403.02683"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+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/dvtailor/meta-l2d","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"ran_violates":1,"unverified":2},"by_repo_kind":{"official":{"samples":9,"ran":7,"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":"7fdf0d5c07ce68e3","entry":"build_mlp","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/modules.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7fdf0d5c07ce68e3"}},{"code_sha256_prefix":"01335dc0f34e678b","entry":"coarse2sparse","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/datasets.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/datasets.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01335dc0f34e678b"}},{"code_sha256_prefix":"6770e1b1b3fc9de1","entry":"evaluate","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"train_classifier.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/train_classifier.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6770e1b1b3fc9de1"}},{"code_sha256_prefix":"312e5f2464fea070","entry":"get_activation","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/modules.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"312e5f2464fea070"}},{"code_sha256_prefix":"2f4965e3468a2cd0","entry":"get_logger","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2f4965e3468a2cd0"}},{"code_sha256_prefix":"089e4f655bd7a447","entry":"ova","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/losses.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/losses.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"089e4f655bd7a447"}},{"code_sha256_prefix":"4e479c89e029d625","entry":"sparse2coarse","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/datasets.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/datasets.py","link_basis":"plan_row","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e479c89e029d625"}},{"code_sha256_prefix":"f0c9a29156911331","entry":"accuracy","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/utils.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f0c9a29156911331"}},{"code_sha256_prefix":"b7973ff91fa76798","entry":"cross_entropy","repo":"dvtailor/meta-l2d","repo_kind":"official","path":"lib/losses.py","file_url":"https://github.com/dvtailor/meta-l2d/blob/HEAD/lib/losses.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b7973ff91fa76798"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}