{"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/federated-learning-using-a-mixture-of-experts","title":"Specialized federated learning using a mixture of experts","arxiv_id":"2010.02056","date":"2020-10-05","proceeding":null,"authors":["Edvin Listo Zec","Olof Mogren","John Martinsson","Leon René Sütfeld","Daniel Gillblad"],"abstract":"In federated learning, clients share a global model that has been trained on decentralized local client data. Although federated learning shows significant promise as a key approach when data cannot be shared or centralized, current methods show limited privacy properties and have shortcomings when applied to common real-world scenarios, especially when client data is heterogeneous. In this paper, we propose an alternative method to learn a personalized model for each client in a federated setting, with greater generalization abilities than previous methods. To achieve this personalization we propose a federated learning framework using a mixture of experts to combine the specialist nature of a locally trained model with the generalist knowledge of a global model. We evaluate our method on a variety of datasets with different levels of data heterogeneity, and our results show that the mixture of experts model is better suited as a personalized model for devices in these settings, outperforming both fine-tuned global models and local specialists.","url_abs":"https://arxiv.org/abs/2010.02056v3","url_pdf":"https://arxiv.org/pdf/2010.02056v3.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":"federated-learning-using-a-mixture-of-experts","repo_url":"https://github.com/edvinli/federated-learning-mixture","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"mixture-of-experts","task_name":"Mixture-of-Experts"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2010.02056","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.02056"}},"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/edvinli/federated-learning-mixture","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":1,"unverified":7},"by_repo_kind":{"official":{"samples":8,"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":0,"samples":[{"code_sha256_prefix":"d9107114749c3e49","entry":"mnist_iid","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"utils/sample_data.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/utils/sample_data.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":"d9107114749c3e49"}},{"code_sha256_prefix":"542a499a7eafaa04","entry":"FedAvg","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"models/FederatedAveraging.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/models/FederatedAveraging.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":"542a499a7eafaa04"}},{"code_sha256_prefix":"e93dc99aaaeb74e7","entry":"agnews_noniid","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"utils/sample_languagedata.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/utils/sample_languagedata.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":"e93dc99aaaeb74e7"}},{"code_sha256_prefix":"ce92e0c1fa3c65a0","entry":"cifar_iid","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"utils/sample_languagedata.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/utils/sample_languagedata.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":"ce92e0c1fa3c65a0"}},{"code_sha256_prefix":"98fe2f24aee60e8c","entry":"cifar_iid2","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"utils/sample_languagedata.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/utils/sample_languagedata.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":"98fe2f24aee60e8c"}},{"code_sha256_prefix":"79660985a20ca0a1","entry":"emnist_iid","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"utils/sample_data.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/utils/sample_data.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":"79660985a20ca0a1"}},{"code_sha256_prefix":"5dc56978c5ae6baf","entry":"evaluate_validation","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"models/LanguageClientUpdate.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/models/LanguageClientUpdate.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":"5dc56978c5ae6baf"}},{"code_sha256_prefix":"80eaa4c2dace63d8","entry":"mnist_noniid","repo":"edvinli/federated-learning-mixture","repo_kind":"official","path":"utils/sample_data.py","file_url":"https://github.com/edvinli/federated-learning-mixture/blob/HEAD/utils/sample_data.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":"80eaa4c2dace63d8"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}