{"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/an-efficient-mini-batch-method-via-partial","title":"Improving Mini-batch Optimal Transport via Partial Transportation","arxiv_id":"2108.09645","date":"2021-08-22","proceeding":null,"authors":["Khai Nguyen","Dang Nguyen","The-Anh Vu-Le","Tung Pham","Nhat Ho"],"abstract":"Mini-batch optimal transport (m-OT) has been widely used recently to deal with the memory issue of OT in large-scale applications. Despite their practicality, m-OT suffers from misspecified mappings, namely, mappings that are optimal on the mini-batch level but are partially wrong in the comparison with the optimal transportation plan between the original measures. Motivated by the misspecified mappings issue, we propose a novel mini-batch method by using partial optimal transport (POT) between mini-batch empirical measures, which we refer to as mini-batch partial optimal transport (m-POT). Leveraging the insight from the partial transportation, we explain the source of misspecified mappings from the m-OT and motivate why limiting the amount of transported masses among mini-batches via POT can alleviate the incorrect mappings. Finally, we carry out extensive experiments on various applications such as deep domain adaptation, partial domain adaptation, deep generative model, color transfer, and gradient flow to demonstrate the favorable performance of m-POT compared to current mini-batch methods.","url_abs":"https://arxiv.org/abs/2108.09645v4","url_pdf":"https://arxiv.org/pdf/2108.09645v4.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":"an-efficient-mini-batch-method-via-partial","repo_url":"https://github.com/ut-austin-data-science-group/mini-batch-ot","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"an-efficient-mini-batch-method-via-partial","repo_url":"https://github.com/khainb/BoMb-OT","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-adaptation","task_name":"Domain Adaptation"},{"task_slug":"partial-domain-adaptation","task_name":"Partial Domain Adaptation"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2108.09645","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2108.09645"}},"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/ut-austin-data-science-group/mini-batch-ot","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/khainb/BoMb-OT","reach":null}],"summary":{"ran":3,"ran_draft_wrong":4,"unverified":4},"by_repo_kind":{"official":{"samples":10,"ran":7,"repositories":2}},"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":1,"samples":[{"code_sha256_prefix":"a2d1ed9ac5b514b0","entry":"BalancedBatchSampler","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.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":"a2d1ed9ac5b514b0"}},{"code_sha256_prefix":"4e7fbdb2bc8ec056","entry":"BoMbOT","repo":"ut-austin-data-science-group/mini-batch-ot","repo_kind":"official","path":"ABC/utils.py","file_url":"https://github.com/ut-austin-data-science-group/mini-batch-ot/blob/HEAD/ABC/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4e7fbdb2bc8ec056"}},{"code_sha256_prefix":"76825d32647cb3ce","entry":"ImageList","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.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":"76825d32647cb3ce"}},{"code_sha256_prefix":"978e1da65a934d3a","entry":"InfiniteSliceIterator","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.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":"978e1da65a934d3a"}},{"code_sha256_prefix":"60166088c825b407","entry":"image_test","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"60166088c825b407"}},{"code_sha256_prefix":"6d14e3fcb8d93fa1","entry":"image_train","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"6d14e3fcb8d93fa1"}},{"code_sha256_prefix":"693fef7015113684","entry":"inv_lr_scheduler","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"693fef7015113684"}},{"code_sha256_prefix":"4fde4b15ac469854","entry":"ResNetFc","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.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":"4fde4b15ac469854"}},{"code_sha256_prefix":"0fa0506a51ba91fa","entry":"VGGFc","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.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":"0fa0506a51ba91fa"}},{"code_sha256_prefix":"b42e76c69ec6ec9c","entry":"image_classification","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":"b42e76c69ec6ec9c"}},{"code_sha256_prefix":"4ecaced2e83b4ff1","entry":"train","repo":"khainb/BoMb-OT","repo_kind":"official","path":"PartialDA/run_mOT.py","file_url":"https://github.com/khainb/BoMb-OT/blob/HEAD/PartialDA/run_mOT.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":"4ecaced2e83b4ff1"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}