{"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/active-learning-helps-pretrained-models-learn","title":"Active Learning Helps Pretrained Models Learn the Intended Task","arxiv_id":"2204.08491","date":"2022-04-18","proceeding":null,"authors":["Alex Tamkin","Dat Nguyen","Salil Deshpande","Jesse Mu","Noah Goodman"],"abstract":"Models can fail in unpredictable ways during deployment due to task ambiguity, when multiple behaviors are consistent with the provided training data. An example is an object classifier trained on red squares and blue circles: when encountering blue squares, the intended behavior is undefined. We investigate whether pretrained models are better active learners, capable of disambiguating between the possible tasks a user may be trying to specify. Intriguingly, we find that better active learning is an emergent property of the pretraining process: pretrained models require up to 5 times fewer labels when using uncertainty-based active learning, while non-pretrained models see no or even negative benefit. We find these gains come from an ability to select examples with attributes that disambiguate the intended behavior, such as rare product categories or atypical backgrounds. These attributes are far more linearly separable in pretrained model's representation spaces vs non-pretrained models, suggesting a possible mechanism for this behavior.","url_abs":"https://arxiv.org/abs/2204.08491v1","url_pdf":"https://arxiv.org/pdf/2204.08491v1.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":"active-learning-helps-pretrained-models-learn","repo_url":"https://github.com/alextamkin/active-learning-pretrained-models","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"active-learning","task_name":"Active Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.08491","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.08491"}},"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/alextamkin/active-learning-pretrained-models","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_draft_wrong":2,"ran_violates":1,"unverified":13},"by_repo_kind":{"official":{"samples":16,"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":0,"samples":[{"code_sha256_prefix":"ee80cf467065076b","entry":"conv1x1","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/architecture.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/architecture.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ee80cf467065076b"}},{"code_sha256_prefix":"f01b8d3901f0b289","entry":"conv3x3","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/architecture.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/architecture.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"f01b8d3901f0b289"}},{"code_sha256_prefix":"7023eb86801bb3a3","entry":"tf2th","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/architecture.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/architecture.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7023eb86801bb3a3"}},{"code_sha256_prefix":"d38eeb648f68f197","entry":"create_dat","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/lbtoolbox.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/lbtoolbox.py","link_basis":"harvester_set","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":"d38eeb648f68f197"}},{"code_sha256_prefix":"0123d0a848b9b0b8","entry":"entropy","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/acquisition.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/acquisition.py","link_basis":"harvester_set","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":"0123d0a848b9b0b8"}},{"code_sha256_prefix":"781e1dfa44bed028","entry":"find_few_shot_subset","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/multi_attr_dataset.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/multi_attr_dataset.py","link_basis":"harvester_set","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":"781e1dfa44bed028"}},{"code_sha256_prefix":"9e433b12009a8d58","entry":"get_losses_and_topks_results","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/train_test_common.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/train_test_common.py","link_basis":"harvester_set","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":"9e433b12009a8d58"}},{"code_sha256_prefix":"7d63034d0bfadd78","entry":"get_mixup","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/hyper_params.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/hyper_params.py","link_basis":"harvester_set","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":"7d63034d0bfadd78"}},{"code_sha256_prefix":"f7f802d7a86c68c5","entry":"get_scaled_resolution","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/datasets/metadata.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/datasets/metadata.py","link_basis":"harvester_set","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":"f7f802d7a86c68c5"}},{"code_sha256_prefix":"2c51b4719ea4c6b9","entry":"get_schedule","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/hyper_params.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/hyper_params.py","link_basis":"harvester_set","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":"2c51b4719ea4c6b9"}},{"code_sha256_prefix":"12109eac56e48b6b","entry":"load_dat","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/lbtoolbox.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/lbtoolbox.py","link_basis":"harvester_set","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":"12109eac56e48b6b"}},{"code_sha256_prefix":"2c8a0fc57eee370a","entry":"minimum_margin","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/acquisition.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/acquisition.py","link_basis":"harvester_set","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":"2c8a0fc57eee370a"}},{"code_sha256_prefix":"2152d1eded7cbdc7","entry":"random","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"models/acquisition.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/models/acquisition.py","link_basis":"harvester_set","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":"2152d1eded7cbdc7"}},{"code_sha256_prefix":"1b8302f01bd10a39","entry":"seed_dataloader_worker","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/train_test_common.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/train_test_common.py","link_basis":"harvester_set","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":"1b8302f01bd10a39"}},{"code_sha256_prefix":"12323f0640436acc","entry":"setup_logger","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/logger.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/logger.py","link_basis":"harvester_set","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":"12323f0640436acc"}},{"code_sha256_prefix":"228b4da98f348fbe","entry":"topk","repo":"alextamkin/active-learning-pretrained-models","repo_kind":"official","path":"utils/train_test_common.py","file_url":"https://github.com/alextamkin/active-learning-pretrained-models/blob/HEAD/utils/train_test_common.py","link_basis":"harvester_set","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":"228b4da98f348fbe"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}