{"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/meta-dmoe-adapting-to-domain-shift-by-meta","title":"Meta-DMoE: Adapting to Domain Shift by Meta-Distillation from Mixture-of-Experts","arxiv_id":"2210.03885","date":"2022-10-08","proceeding":null,"authors":["Tao Zhong","Zhixiang Chi","Li Gu","Yang Wang","Yuanhao Yu","Jin Tang"],"abstract":"In this paper, we tackle the problem of domain shift. Most existing methods perform training on multiple source domains using a single model, and the same trained model is used on all unseen target domains. Such solutions are sub-optimal as each target domain exhibits its own specialty, which is not adapted. Furthermore, expecting single-model training to learn extensive knowledge from multiple source domains is counterintuitive. The model is more biased toward learning only domain-invariant features and may result in negative knowledge transfer. In this work, we propose a novel framework for unsupervised test-time adaptation, which is formulated as a knowledge distillation process to address domain shift. Specifically, we incorporate Mixture-of-Experts (MoE) as teachers, where each expert is separately trained on different source domains to maximize their specialty. Given a test-time target domain, a small set of unlabeled data is sampled to query the knowledge from MoE. As the source domains are correlated to the target domains, a transformer-based aggregator then combines the domain knowledge by examining the interconnection among them. The output is treated as a supervision signal to adapt a student prediction network toward the target domain. We further employ meta-learning to enforce the aggregator to distill positive knowledge and the student network to achieve fast adaptation. Extensive experiments demonstrate that the proposed method outperforms the state-of-the-art and validates the effectiveness of each proposed component. Our code is available at https://github.com/n3il666/Meta-DMoE.","url_abs":"https://arxiv.org/abs/2210.03885v2","url_pdf":"https://arxiv.org/pdf/2210.03885v2.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":"meta-dmoe-adapting-to-domain-shift-by-meta","repo_url":"https://github.com/n3il666/meta-dmoe","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"domain-generalization","task_name":"Domain Generalization"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"},{"task_slug":"meta-learning","task_name":"Meta-Learning"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"},{"task_slug":"test-time-adaptation","task_name":"Test-time Adaptation"},{"task_slug":"transfer-learning","task_name":"Transfer Learning"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/domain-generalization-on-domainnet","task":"Domain Generalization","dataset":"DomainNet","model":"Meta-DMoE (ResNet-50)","rank_in_archive_order":33,"of":38,"metrics":{"Average Accuracy":"44.2"},"uses_additional_data":false},{"leaderboard":"/sota/domain-generalization-on-pacs-2","task":"Domain Generalization","dataset":"PACS","model":"Meta-DMoE (ResNet-50)","rank_in_archive_order":42,"of":133,"metrics":{"Average Accuracy":"86.9"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2210.03885","atlas_url":"https://app.syntology.ai/?focus=2210.03885","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.03885"}},"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":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/n3il666/meta-dmoe","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4,"unverified":3},"by_repo_kind":{"official":{"samples":7,"ran":4,"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":"f6e35c72666b64f6","entry":"get_model_accuracy","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/camelyon/camelyon_experts.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/camelyon/camelyon_experts.py","link_basis":"harvester_set","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":"f6e35c72666b64f6"}},{"code_sha256_prefix":"e2705ed6b48d20e5","entry":"get_selector_accuracy","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/fmow/fmow_aggregator.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/fmow/fmow_aggregator.py","link_basis":"harvester_set","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":"e2705ed6b48d20e5"}},{"code_sha256_prefix":"48d7a611a78faa01","entry":"initialize_image_base_transform","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/camelyon/camelyon_utils.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/camelyon/camelyon_utils.py","link_basis":"harvester_set","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":"48d7a611a78faa01"}},{"code_sha256_prefix":"69e94cb234255b0c","entry":"initialize_image_base_transform","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/fmow/fmow_utils.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/fmow/fmow_utils.py","link_basis":"harvester_set","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":"69e94cb234255b0c"}},{"code_sha256_prefix":"a952a1fa7c7d8616","entry":"get_expert_split","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/camelyon/camelyon_experts.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/camelyon/camelyon_experts.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":"a952a1fa7c7d8616"}},{"code_sha256_prefix":"f2746799d8f51cf0","entry":"get_model_accuracy","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/fmow/fmow_experts.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/fmow/fmow_experts.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":"f2746799d8f51cf0"}},{"code_sha256_prefix":"c71f59f1661f12e4","entry":"get_selector_accuracy","repo":"n3il666/meta-dmoe","repo_kind":"official","path":"src/camelyon/camelyon_aggregator.py","file_url":"https://github.com/n3il666/meta-dmoe/blob/HEAD/src/camelyon/camelyon_aggregator.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":"c71f59f1661f12e4"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}