{"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/learning-to-generalize-meta-learning-for","title":"Learning to Generalize: Meta-Learning for Domain Generalization","arxiv_id":"1710.03463","date":"2017-10-10","proceeding":null,"authors":["Da Li","Yongxin Yang","Yi-Zhe Song","Timothy M. Hospedales"],"abstract":"Domain shift refers to the well known problem that a model trained in one\nsource domain performs poorly when applied to a target domain with different\nstatistics. {Domain Generalization} (DG) techniques attempt to alleviate this\nissue by producing models which by design generalize well to novel testing\ndomains. We propose a novel {meta-learning} method for domain generalization.\nRather than designing a specific model that is robust to domain shift as in\nmost previous DG work, we propose a model agnostic training procedure for DG.\nOur algorithm simulates train/test domain shift during training by synthesizing\nvirtual testing domains within each mini-batch. The meta-optimization objective\nrequires that steps to improve training domain performance should also improve\ntesting domain performance. This meta-learning procedure trains models with\ngood generalization ability to novel domains. We evaluate our method and\nachieve state of the art results on a recent cross-domain image classification\nbenchmark, as well demonstrating its potential on two classic reinforcement\nlearning tasks.","url_abs":"http://arxiv.org/abs/1710.03463v1","url_pdf":"http://arxiv.org/pdf/1710.03463v1.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":"learning-to-generalize-meta-learning-for","repo_url":"https://github.com/HAHA-DL/MLDG","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"learning-to-generalize-meta-learning-for","repo_url":"https://github.com/Pulkit-Khandelwal/medical-mldg-seg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"learning-to-generalize-meta-learning-for","repo_url":"https://github.com/Pulkit-Khandelwal/mldg","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"learning-to-generalize-meta-learning-for","repo_url":"https://github.com/facebookresearch/DomainBed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"learning-to-generalize-meta-learning-for","repo_url":"https://github.com/thuml/Transfer-Learning-Library","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"MLDG (Alexnet)","rank_in_archive_order":124,"of":133,"metrics":{"Average Accuracy":"70.01"},"uses_additional_data":false}],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1710.03463","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1710.03463"}},"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/facebookresearch/DomainBed","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/HAHA-DL/MLDG","reach":{"status":"ok","spdx":"MIT"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/thuml/Transfer-Learning-Library","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pulkit-Khandelwal/medical-mldg-seg","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Pulkit-Khandelwal/mldg","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2,"unverified":9},"by_repo_kind":{"listed":{"samples":11,"ran":2,"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":0,"samples":[{"code_sha256_prefix":"a2d01766b58dccb1","entry":"default_flist_reader","repo":"Pulkit-Khandelwal/mldg","repo_kind":"listed","path":"data_reader.py","file_url":"https://github.com/Pulkit-Khandelwal/mldg/blob/HEAD/data_reader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a2d01766b58dccb1"}},{"code_sha256_prefix":"ac269a0e4b8d946e","entry":"default_loader","repo":"Pulkit-Khandelwal/mldg","repo_kind":"listed","path":"data_reader.py","file_url":"https://github.com/Pulkit-Khandelwal/mldg/blob/HEAD/data_reader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac269a0e4b8d946e"}},{"code_sha256_prefix":"0e943019e82fc2c6","entry":"conv2d","repo":"HAHA-DL/MLDG","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/ops.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":"0e943019e82fc2c6"}},{"code_sha256_prefix":"de1ae463b706fe80","entry":"conv2d","repo":"Pulkit-Khandelwal/mldg","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/Pulkit-Khandelwal/mldg/blob/HEAD/ops.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":"de1ae463b706fe80"}},{"code_sha256_prefix":"784b369d16cde8f9","entry":"linear","repo":"HAHA-DL/MLDG","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/ops.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":"784b369d16cde8f9"}},{"code_sha256_prefix":"982640b2b87ab733","entry":"relu","repo":"HAHA-DL/MLDG","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/ops.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":"982640b2b87ab733"}},{"code_sha256_prefix":"ffc6304fe71748bf","entry":"relu","repo":"Pulkit-Khandelwal/mldg","repo_kind":"listed","path":"ops.py","file_url":"https://github.com/Pulkit-Khandelwal/mldg/blob/HEAD/ops.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":"ffc6304fe71748bf"}},{"code_sha256_prefix":"e66d8098b50090e3","entry":"shuffle_data","repo":"HAHA-DL/MLDG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/utils.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":"e66d8098b50090e3"}},{"code_sha256_prefix":"c63cc42fd5b3834f","entry":"shuffle_list","repo":"HAHA-DL/MLDG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/utils.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":"c63cc42fd5b3834f"}},{"code_sha256_prefix":"704f4addaa30438d","entry":"unfold_label","repo":"HAHA-DL/MLDG","repo_kind":"listed","path":"utils.py","file_url":"https://github.com/HAHA-DL/MLDG/blob/HEAD/utils.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":"704f4addaa30438d"}},{"code_sha256_prefix":"825eed11509a6aa2","entry":"yo","repo":"Pulkit-Khandelwal/mldg","repo_kind":"listed","path":"mlp2.py","file_url":"https://github.com/Pulkit-Khandelwal/mldg/blob/HEAD/mlp2.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":"825eed11509a6aa2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}