{"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/on-the-benefits-of-selectivity-in-pseudo","title":"On Balancing Bias and Variance in Unsupervised Multi-Source-Free Domain Adaptation","arxiv_id":"2202.00796","date":"2022-02-01","proceeding":null,"authors":["Maohao Shen","Yuheng Bu","Gregory Wornell"],"abstract":"Due to privacy, storage, and other constraints, there is a growing need for unsupervised domain adaptation techniques in machine learning that do not require access to the data used to train a collection of source models. Existing methods for multi-source-free domain adaptation (MSFDA) typically train a target model using pseudo-labeled data produced by the source models, which focus on improving the pseudo-labeling techniques or proposing new training objectives. Instead, we aim to analyze the fundamental limits of MSFDA. In particular, we develop an information-theoretic bound on the generalization error of the resulting target model, which illustrates an inherent bias-variance trade-off. We then provide insights on how to balance this trade-off from three perspectives, including domain aggregation, selective pseudo-labeling, and joint feature alignment, which leads to the design of novel algorithms. Experiments on multiple datasets validate our theoretical analysis and demonstrate the state-of-art performance of the proposed algorithm, especially on some of the most challenging datasets, including Office-Home and DomainNet.","url_abs":"https://arxiv.org/abs/2202.00796v3","url_pdf":"https://arxiv.org/pdf/2202.00796v3.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":"on-the-benefits-of-selectivity-in-pseudo","repo_url":"https://github.com/maohaos2/MSFDA","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"source-free-domain-adaptation","task_name":"Source-Free Domain Adaptation"},{"task_slug":"unsupervised-domain-adaptation","task_name":"Unsupervised Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2202.00796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2202.00796"}},"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/maohaos2/MSFDA","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":5,"ran_honours":2,"unverified":4},"by_repo_kind":{"official":{"samples":11,"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":"94b5622f0aa7add1","entry":"Entropy","repo":"maohaos2/MSFDA","repo_kind":"official","path":"loss.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/loss.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"94b5622f0aa7add1"}},{"code_sha256_prefix":"6e4265b7f707b718","entry":"image_test","repo":"maohaos2/MSFDA","repo_kind":"official","path":"adapt.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/adapt.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6e4265b7f707b718"}},{"code_sha256_prefix":"35c2d572ebd185f5","entry":"image_train","repo":"maohaos2/MSFDA","repo_kind":"official","path":"train_source.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/train_source.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"35c2d572ebd185f5"}},{"code_sha256_prefix":"edd7184ac144c4fa","entry":"l_loader","repo":"maohaos2/MSFDA","repo_kind":"official","path":"data_list.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/data_list.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"edd7184ac144c4fa"}},{"code_sha256_prefix":"0b7ffc9f8b77529c","entry":"lr_scheduler","repo":"maohaos2/MSFDA","repo_kind":"official","path":"train_source.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/train_source.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0b7ffc9f8b77529c"}},{"code_sha256_prefix":"93a11f62e4a129f0","entry":"op_copy","repo":"maohaos2/MSFDA","repo_kind":"official","path":"adapt.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/adapt.py","link_basis":"plan_row","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"93a11f62e4a129f0"}},{"code_sha256_prefix":"2c5ce24ea2b5d2a4","entry":"rgb_loader","repo":"maohaos2/MSFDA","repo_kind":"official","path":"data_list.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/data_list.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c5ce24ea2b5d2a4"}},{"code_sha256_prefix":"9c0d2ceeef4fc6b3","entry":"image_train","repo":"maohaos2/MSFDA","repo_kind":"official","path":"adapt.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/adapt.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":"9c0d2ceeef4fc6b3"}},{"code_sha256_prefix":"09ad767f042450a8","entry":"make_dataset","repo":"maohaos2/MSFDA","repo_kind":"official","path":"data_list.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/data_list.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":"09ad767f042450a8"}},{"code_sha256_prefix":"b3121e5da47857cc","entry":"mutual_info_loss","repo":"maohaos2/MSFDA","repo_kind":"official","path":"loss.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/loss.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":"b3121e5da47857cc"}},{"code_sha256_prefix":"1b78e684c8183c16","entry":"prototype_weights","repo":"maohaos2/MSFDA","repo_kind":"official","path":"loss.py","file_url":"https://github.com/maohaos2/MSFDA/blob/HEAD/loss.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":"1b78e684c8183c16"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}