{"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/free-lunch-for-domain-adversarial-training-1","title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing","arxiv_id":"2302.00194","date":"2023-02-01","proceeding":"The Eleventh International Conference on Learning Representations (ICLR 2023) 2023 1","authors":["Yifan Zhang","Xue Wang","Jian Liang","Zhang Zhang","Liang Wang","Rong Jin","Tieniu Tan"],"abstract":"A fundamental challenge for machine learning models is how to generalize learned models for out-of-distribution (OOD) data. Among various approaches, exploiting invariant features by Domain Adversarial Training (DAT) received widespread attention. Despite its success, we observe training instability from DAT, mostly due to over-confident domain discriminator and environment label noise. To address this issue, we proposed Environment Label Smoothing (ELS), which encourages the discriminator to output soft probability, which thus reduces the confidence of the discriminator and alleviates the impact of noisy environment labels. We demonstrate, both experimentally and theoretically, that ELS can improve training stability, local convergence, and robustness to noisy environment labels. By incorporating ELS with DAT methods, we are able to yield state-of-art results on a wide range of domain generalization/adaptation tasks, particularly when the environment labels are highly noisy.","url_abs":"https://arxiv.org/abs/2302.00194v1","url_pdf":"https://arxiv.org/pdf/2302.00194v1.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":"free-lunch-for-domain-adversarial-training-1","repo_url":"https://github.com/yfzhang114/Environment-Label-Smoothing","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"}],"methods":[{"method_slug":"label-smoothing","method_name":"Label Smoothing"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-adaptation-on-office-31","task":"Domain Adaptation","dataset":"Office-31","model":"ELS","rank_in_archive_order":12,"of":40,"metrics":{"Average Accuracy":"90.4"},"uses_additional_data":false},{"leaderboard":"/sota/domain-adaptation-on-office-home","task":"Domain Adaptation","dataset":"Office-Home","model":"ELS","rank_in_archive_order":8,"of":29,"metrics":{"Accuracy":"84.6"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2302.00194","atlas_url":"https://app.syntology.ai/?focus=2302.00194","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2302.00194"}},"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":"deterministic:regex_extraction","url":"https://github.com/yfzhang114/Environment-Label-Smoothing","reach":null}],"summary":{"ran_draft_wrong":1,"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":1,"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":2,"samples":[{"code_sha256_prefix":"f0b9793b30a672e0","entry":"cross_entropy_loss","repo":"yfzhang114/Environment-Label-Smoothing","repo_kind":"official","path":"Domain_Generalization/domainbed/algorithms.py","file_url":"https://github.com/yfzhang114/Environment-Label-Smoothing/blob/HEAD/Domain_Generalization/domainbed/algorithms.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"f0b9793b30a672e0"}},{"code_sha256_prefix":"b0bc80b1655a6802","entry":"get_algorithm_class","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"b0bc80b1655a6802"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}