{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/when-does-bias-transfer-in-transfer-learning","title":"When does Bias Transfer in Transfer Learning?","arxiv_id":"2207.02842","date":"2022-07-06","proceeding":null,"authors":["Hadi Salman","Saachi Jain","Andrew Ilyas","Logan Engstrom","Eric Wong","Aleksander Madry"],"abstract":"Using transfer learning to adapt a pre-trained \"source model\" to a downstream \"target task\" can dramatically increase performance with seemingly no downside. In this work, we demonstrate that there can exist a downside after all: bias transfer, or the tendency for biases of the source model to persist even after adapting the model to the target class. Through a combination of synthetic and natural experiments, we show that bias transfer both (a) arises in realistic settings (such as when pre-training on ImageNet or other standard datasets) and (b) can occur even when the target dataset is explicitly de-biased. As transfer-learned models are increasingly deployed in the real world, our work highlights the importance of understanding the limitations of pre-trained source models. Code is available at https://github.com/MadryLab/bias-transfer","url_abs":"https://arxiv.org/abs/2207.02842v1","url_pdf":"https://arxiv.org/pdf/2207.02842v1.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":"when-does-bias-transfer-in-transfer-learning","repo_url":"https://github.com/MadryLab/bias-transfer","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2207.02842","atlas_url":"https://app.syntology.ai/?focus=2207.02842","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2207.02842"},"calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.02842"},"returns":"the samples harvested from this paper, each with its run record; it does not verify the paper"},{"tool":"get_code","arguments_in":"samples[].code_sha256","returns":"one stored sample by its code_sha256; not shown on this site"}]},"developers":"https://syntology.ai/developers","held":true,"reason":"in_graph_layer","checked_against":null,"agent_calls":[{"tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2207.02842"},"call":"get_harvested_code_for_paper(arxiv_id=\"2207.02842\")"},{"tool":"get_code","arguments_in":{"code_sha256":"syntology.samples[].code_sha256"},"call":"get_code(code_sha256=\"…\")"},{"tool":"get_citation_path","arguments":{"paper_1":"2207.02842"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2207.02842\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2207.02842"},"call":"get_concepts_for_paper(arxiv_id=\"2207.02842\")"}],"by_repo":[{"repo":"MadryLab/bias-transfer","kind":"official","samples":10,"ran":7,"instrument":0,"unverified":3}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code","read_at":"2026-10-05T00:36:11+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","ran_record":{"url":"https://syntology.ai/api/ran/2207.02842.json","schema":"syntology.ran_record/1","counts_crosswalk":{"n_samples":"syntology.counts.lifted","n_ran":"syntology.counts.executed","n_ran_checked":"syntology.counts.checked","n_instrument":"syntology.counts.instrument_failures","n_unverified":"syntology.counts.no_recorded_run"},"note":"live record, measured at request time; may be newer than this page's graph read","badge":"https://syntology.ai/api/ran/2207.02842.svg"},"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/MadryLab/bias-transfer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":7,"unverified":3},"n_samples":10,"n_ran":7,"n_constructed":0,"n_ran_checked":7,"n_instrument":0,"n_unverified":3,"n_instrument_is":"failures of Syntology's instrument, not of the code","every_run_is_an_instrument_failure":false,"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"by_repo_kind":{"official":{"samples":10,"ran":7,"n_ran_checked":7,"n_instrument":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,"inline_ok_is":"inline_ok is true only when both licence gates allow Syntology to serve this code's text: this paper's link (inline_ok_link, from the licence of this paper's copy) and the stored copy of the same code that Syntology serves, which may have been first harvested from another repository. withheld_clause is Syntology's own wording of which gate keeps the text a pointer and why, and is null when inline_ok is true. This site shows no code text either way; n_pointer_only_for_licence counts samples with inline_ok false (both gates), n_pointer_only_link_allows those of them whose inline_ok_link is true","n_pointer_only_link_allows":0,"fixture_fields_is":{"signature_and_fixture_out_type":"the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right","level_recorded_at":"when Syntology's graph wrote the sample's verification level, not when the code executed; absent where the level was written before the date was kept, and never filled in with the build date","present_on":"samples that ran only; a key is absent, never empty, where the graph records nothing"},"n_ran_with_level_date":7,"n_ran_without_level_date":0,"n_ran_signature_not_shown":0,"levels_written_between":{"first":"2026-09-25","last":"2026-09-25","is":"the first and last UTC dates on which Syntology's graph wrote a verification level for a sample on this page that ran, not when the code executed"},"code_page_min_papers":5,"code_page_is":"a page for the entry name across every paper's harvested code; the name is a string, not an identity","samples":[{"code_sha256":"e528e1ef2fec63df","code_sha256_prefix":"e528e1ef2fec63df","entry":"build_model","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model_building_args:dict/0/?","fixture_out_type":"TransferNetwork","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":"/code/build-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"e528e1ef2fec63df"}},{"code_sha256":"db3563326e1ddc10","code_sha256_prefix":"db3563326e1ddc10","entry":"build_source_model","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/models.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"arch:str/0/str, num_classes:int/0/int, pretrained:bool/0/bool","fixture_out_type":"ResNet","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"db3563326e1ddc10"}},{"code_sha256":"2bd9ba841b22a533","code_sha256_prefix":"2bd9ba841b22a533","entry":"convert_fastargs","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/config_parse_utils.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/config_parse_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"fast_args:SimpleNamespace/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"2bd9ba841b22a533"}},{"code_sha256":"8e3e794b7f3dd5f7","code_sha256_prefix":"8e3e794b7f3dd5f7","entry":"evaluate_model","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/eval_utils.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/eval_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"model:callable/0/?, loader:list/1/tuple, num_classes:int/0/int, granularity:str/0/str, name:NoneType/0/?","fixture_out_type":"dict","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":"/code/evaluate-model","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"8e3e794b7f3dd5f7"}},{"code_sha256":"194c6951a2cf7d0e","code_sha256_prefix":"194c6951a2cf7d0e","entry":"get_optimizer_and_lr_scheduler","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/optimizers.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/optimizers.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"training_args:dict/0/?, model:callable/0/?, iters_per_epoch:int/0/int","fixture_out_type":"tuple","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"194c6951a2cf7d0e"}},{"code_sha256":"93ab68302cd1eac2","code_sha256_prefix":"93ab68302cd1eac2","entry":"inv_norm","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/loaders.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/loaders.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"ds_name:str/0/str","fixture_out_type":"Compose","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"93ab68302cd1eac2"}},{"code_sha256":"d7853049a9701459","code_sha256_prefix":"d7853049a9701459","entry":"read_yaml","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/config_parse_utils.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/config_parse_utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"signature":"yaml_dir:str/0/str","fixture_out_type":"dict","level_recorded_at":"2026-09-25T06:32:53.441431+00:00","code_page":"/code/read-yaml","census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"d7853049a9701459"}},{"code_sha256":"f41852bd75e525c2","code_sha256_prefix":"f41852bd75e525c2","entry":"build_transfer_model","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/models.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/models.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"f41852bd75e525c2"}},{"code_sha256":"21db9a02a5e09164","code_sha256_prefix":"21db9a02a5e09164","entry":"get_spurious_indices","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/embed_spurious.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/embed_spurious.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"21db9a02a5e09164"}},{"code_sha256":"7f16e0e5db7b1569","code_sha256_prefix":"7f16e0e5db7b1569","entry":"get_training_loaders","repo":"MadryLab/bias-transfer","repo_kind":"official","path":"src/facial_recognition.py","file_url":"https://github.com/MadryLab/bias-transfer/blob/HEAD/src/facial_recognition.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"code_page":null,"census":null,"licence":"MIT","inline_ok":true,"inline_ok_link":true,"withheld_clause":null,"mcp_get_code":{"code_sha256":"7f16e0e5db7b1569"}}]},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"0306ad685f9440488049626eeb6dee09027f2767217f20da14b8fac09a269138","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}