{"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/sparsyfed-sparse-adaptive-federated-training","title":"SparsyFed: Sparse Adaptive Federated Training","arxiv_id":"2504.05153","date":"2025-04-07","proceeding":null,"authors":["Adriano Guastella","Lorenzo Sani","Alex Iacob","Alessio Mora","Paolo Bellavista","Nicholas D. Lane"],"abstract":"Sparse training is often adopted in cross-device federated learning (FL) environments where constrained devices collaboratively train a machine learning model on private data by exchanging pseudo-gradients across heterogeneous networks. Although sparse training methods can reduce communication overhead and computational burden in FL, they are often not used in practice for the following key reasons: (1) data heterogeneity makes it harder for clients to reach consensus on sparse models compared to dense ones, requiring longer training; (2) methods for obtaining sparse masks lack adaptivity to accommodate very heterogeneous data distributions, crucial in cross-device FL; and (3) additional hyperparameters are required, which are notably challenging to tune in FL. This paper presents SparsyFed, a practical federated sparse training method that critically addresses the problems above. Previous works have only solved one or two of these challenges at the expense of introducing new trade-offs, such as clients' consensus on masks versus sparsity pattern adaptivity. We show that SparsyFed simultaneously (1) can produce 95% sparse models, with negligible degradation in accuracy, while only needing a single hyperparameter, (2) achieves a per-round weight regrowth 200 times smaller than previous methods, and (3) allows the sparse masks to adapt to highly heterogeneous data distributions and outperform all baselines under such conditions.","url_abs":"https://arxiv.org/abs/2504.05153v1","url_pdf":"https://arxiv.org/pdf/2504.05153v1.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":"sparsyfed-sparse-adaptive-federated-training","repo_url":"https://github.com/aguastella/sparsyfed","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2504.05153","atlas_url":"https://app.syntology.ai/?focus=2504.05153","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.05153"}},"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/aguastella/sparsyfed","reach":null}],"summary":{"ran":2,"ran_draft_wrong":3,"unverified":1},"by_repo_kind":{"official":{"samples":6,"ran":5,"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":6,"samples":[{"code_sha256_prefix":"7ab1cd3f6a101c52","entry":"SpectralNormHandler","repo":"aguastella/sparsyfed","repo_kind":"official","path":"project/task/utils/sparsyfed_modules.py","file_url":"https://github.com/aguastella/sparsyfed/blob/HEAD/project/task/utils/sparsyfed_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"7ab1cd3f6a101c52"}},{"code_sha256_prefix":"4b1cbcf3c466e1b1","entry":"get_tensor_sparsity","repo":"aguastella/sparsyfed","repo_kind":"official","path":"project/task/utils/sparsyfed_modules.py","file_url":"https://github.com/aguastella/sparsyfed/blob/HEAD/project/task/utils/sparsyfed_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"4b1cbcf3c466e1b1"}},{"code_sha256_prefix":"0ba54f3e3697b9e3","entry":"matrix_drop","repo":"aguastella/sparsyfed","repo_kind":"official","path":"project/task/utils/sparsyfed_modules.py","file_url":"https://github.com/aguastella/sparsyfed/blob/HEAD/project/task/utils/sparsyfed_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0ba54f3e3697b9e3"}},{"code_sha256_prefix":"fe61a953ac637897","entry":"matrix_drop_th","repo":"aguastella/sparsyfed","repo_kind":"official","path":"project/task/utils/sparsyfed_modules.py","file_url":"https://github.com/aguastella/sparsyfed/blob/HEAD/project/task/utils/sparsyfed_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"fe61a953ac637897"}},{"code_sha256_prefix":"85abdd27cc16764d","entry":"sparsyfed_linear","repo":"aguastella/sparsyfed","repo_kind":"official","path":"project/task/utils/sparsyfed_modules.py","file_url":"https://github.com/aguastella/sparsyfed/blob/HEAD/project/task/utils/sparsyfed_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"85abdd27cc16764d"}},{"code_sha256_prefix":"36525616438ce5e9","entry":"SparsyFedLinear","repo":"aguastella/sparsyfed","repo_kind":"official","path":"project/task/utils/sparsyfed_modules.py","file_url":"https://github.com/aguastella/sparsyfed/blob/HEAD/project/task/utils/sparsyfed_modules.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"36525616438ce5e9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}