{"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/the-panaceas-for-improving-low-rank","title":"The Panaceas for Improving Low-Rank Decomposition in Communication-Efficient Federated Learning","arxiv_id":"2505.23176","date":"2025-05-29","proceeding":null,"authors":["Shiwei Li","Xiandi Luo","Haozhao Wang","Xing Tang","Shijie Xu","Weihong Luo","Yuhua Li","Xiuqiang He","Ruixuan Li"],"abstract":"To improve the training efficiency of federated learning (FL), previous research has employed low-rank decomposition techniques to reduce communication overhead. In this paper, we seek to enhance the performance of these low-rank decomposition methods. Specifically, we focus on three key issues related to decomposition in FL: what to decompose, how to decompose, and how to aggregate. Subsequently, we introduce three novel techniques: Model Update Decomposition (MUD), Block-wise Kronecker Decomposition (BKD), and Aggregation-Aware Decomposition (AAD), each targeting a specific issue. These techniques are complementary and can be applied simultaneously to achieve optimal performance. Additionally, we provide a rigorous theoretical analysis to ensure the convergence of the proposed MUD. Extensive experimental results show that our approach achieves faster convergence and superior accuracy compared to relevant baseline methods. The code is available at https://github.com/Leopold1423/fedmud-icml25.","url_abs":"https://arxiv.org/abs/2505.23176v1","url_pdf":"https://arxiv.org/pdf/2505.23176v1.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":"the-panaceas-for-improving-low-rank","repo_url":"https://github.com/leopold1423/fedmud-icml25","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[{"method_slug":"focus","method_name":"Focus"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2505.23176","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23176"}},"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/leopold1423/fedmud-icml25","reach":null}],"summary":{"ran":2,"ran_draft_wrong":3,"ran_honours":1,"unverified":3},"by_repo_kind":{"official":{"samples":8,"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":9,"samples":[{"code_sha256_prefix":"343422173eec4c92","entry":"Kron_Update","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"decompose/dmu.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/decompose/dmu.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":"343422173eec4c92"}},{"code_sha256_prefix":"8324e811878e3b05","entry":"Kron_Weight","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"decompose/dmu.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/decompose/dmu.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":"8324e811878e3b05"}},{"code_sha256_prefix":"e4982bcb957e1842","entry":"partition_train_data","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"dataloader/datapartition.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/dataloader/datapartition.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"e4982bcb957e1842"}},{"code_sha256_prefix":"a1b6b6404ceaede9","entry":"print_client_data_stats","repo":null,"repo_kind":null,"path":null,"file_url":null,"link_basis":"identical_code_first_harvested_elsewhere","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":null,"inline_ok":false,"mcp_get_code":{"code_sha256":"a1b6b6404ceaede9"}},{"code_sha256_prefix":"efd45416873e40d6","entry":"test","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"train/trainer.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/train/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"efd45416873e40d6"}},{"code_sha256_prefix":"27cbdeab90a7fc0d","entry":"train","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"train/trainer.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/train/trainer.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27cbdeab90a7fc0d"}},{"code_sha256_prefix":"7c850ba861b15a63","entry":"dmu_push_reset_update","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"decompose/dmu.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/decompose/dmu.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":"7c850ba861b15a63"}},{"code_sha256_prefix":"3a322b310819b71a","entry":"kron_3d","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"decompose/dmu.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/decompose/dmu.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":"3a322b310819b71a"}},{"code_sha256_prefix":"81aeac60eb139a7c","entry":"kron_3d","repo":"leopold1423/fedmud-icml25","repo_kind":"official","path":"decompose/dmu.py","file_url":"https://github.com/leopold1423/fedmud-icml25/blob/HEAD/decompose/dmu.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":"81aeac60eb139a7c"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}