{"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/efficient-split-mix-federated-learning-for-on-1","title":"Efficient Split-Mix Federated Learning for On-Demand and In-Situ Customization","arxiv_id":"2203.09747","date":"2022-03-18","proceeding":"ICLR 2022 4","authors":["Junyuan Hong","Haotao Wang","Zhangyang Wang","Jiayu Zhou"],"abstract":"Federated learning (FL) provides a distributed learning framework for multiple participants to collaborate learning without sharing raw data. In many practical FL scenarios, participants have heterogeneous resources due to disparities in hardware and inference dynamics that require quickly loading models of different sizes and levels of robustness. The heterogeneity and dynamics together impose significant challenges to existing FL approaches and thus greatly limit FL's applicability. In this paper, we propose a novel Split-Mix FL strategy for heterogeneous participants that, once training is done, provides in-situ customization of model sizes and robustness. Specifically, we achieve customization by learning a set of base sub-networks of different sizes and robustness levels, which are later aggregated on-demand according to inference requirements. This split-mix strategy achieves customization with high efficiency in communication, storage, and inference. Extensive experiments demonstrate that our method provides better in-situ customization than the existing heterogeneous-architecture FL methods. Codes and pre-trained models are available: https://github.com/illidanlab/SplitMix.","url_abs":"https://arxiv.org/abs/2203.09747v1","url_pdf":"https://arxiv.org/pdf/2203.09747v1.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":"efficient-split-mix-federated-learning-for-on-1","repo_url":"https://github.com/illidanlab/SplitMix","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"personalized-federated-learning","task_name":"Personalized Federated Learning"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2203.09747","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2203.09747"}},"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/illidanlab/SplitMix","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"unverified":11},"by_repo_kind":{"official":{"samples":11,"ran":0,"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":"624f5821bd9f2daa","entry":"count_params_by_state","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/profile_func.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/profile_func.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":"624f5821bd9f2daa"}},{"code_sha256_prefix":"c1f9c3bdd753a577","entry":"counter_norm","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/thop_op_hooks.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/thop_op_hooks.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":"c1f9c3bdd753a577"}},{"code_sha256_prefix":"fc1cb71e81ffc3fa","entry":"counter_softmax","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/thop_op_hooks.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/thop_op_hooks.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":"fc1cb71e81ffc3fa"}},{"code_sha256_prefix":"f2666ef16161746f","entry":"get_bn_layer","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/bn_ops.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/bn_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":"f2666ef16161746f"}},{"code_sha256_prefix":"92176cf63686ae8d","entry":"get_model_fh","repo":"illidanlab/SplitMix","repo_kind":"official","path":"fed_hfl.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/fed_hfl.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":"92176cf63686ae8d"}},{"code_sha256_prefix":"4fa0fb6d78f7d19d","entry":"get_model_fh","repo":"illidanlab/SplitMix","repo_kind":"official","path":"fedavg.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/fedavg.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":"4fa0fb6d78f7d19d"}},{"code_sha256_prefix":"2cfcc2cd96c72207","entry":"get_slim_ratios_from_str","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/slimmable_models.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/slimmable_models.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":"2cfcc2cd96c72207"}},{"code_sha256_prefix":"8df4be770640f030","entry":"is_film_dual_norm","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/bn_ops.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/bn_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":"8df4be770640f030"}},{"code_sha256_prefix":"8bfb46d01decb53f","entry":"kaiming_uniform_in_","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/models.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/models.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":"8bfb46d01decb53f"}},{"code_sha256_prefix":"42ad6079acf38b70","entry":"parse_lognorm_slim_schedule","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/slimmable_models.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/slimmable_models.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":"42ad6079acf38b70"}},{"code_sha256_prefix":"62d1f031086e9acf","entry":"scale_init_param","repo":"illidanlab/SplitMix","repo_kind":"official","path":"nets/models.py","file_url":"https://github.com/illidanlab/SplitMix/blob/HEAD/nets/models.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":"62d1f031086e9acf"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}