{"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/communication-efficient-vertical-federated-1","title":"Communication-efficient Vertical Federated Learning via Compressed Error Feedback","arxiv_id":"2406.14420","date":"2024-06-20","proceeding":null,"authors":["Pedro Valdeira","João Xavier","Cláudia Soares","Yuejie Chi"],"abstract":"Communication overhead is a known bottleneck in federated learning (FL). To address this, lossy compression is commonly used on the information communicated between the server and clients during training. In horizontal FL, where each client holds a subset of the samples, such communication-compressed training methods have recently seen significant progress. However, in their vertical FL counterparts, where each client holds a subset of the features, our understanding remains limited. To address this, we propose an error feedback compressed vertical federated learning (EF-VFL) method to train split neural networks. In contrast to previous communication-compressed methods for vertical FL, EF-VFL does not require a vanishing compression error for the gradient norm to converge to zero for smooth nonconvex problems. By leveraging error feedback, our method can achieve a $\\mathcal{O}(1/T)$ convergence rate for a sufficiently large batch size, improving over the state-of-the-art $\\mathcal{O}(1/\\sqrt{T})$ rate under $\\mathcal{O}(1/\\sqrt{T})$ compression error, and matching the rate of uncompressed methods. Further, when the objective function satisfies the Polyak-{\\L}ojasiewicz inequality, our method converges linearly. In addition to improving convergence, our method also supports the use of private labels. Numerical experiments show that EF-VFL significantly improves over the prior art, confirming our theoretical results. The code for this work can be found at https://github.com/Valdeira/EF-VFL.","url_abs":"https://arxiv.org/abs/2406.14420v3","url_pdf":"https://arxiv.org/pdf/2406.14420v3.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":"communication-efficient-vertical-federated-1","repo_url":"https://github.com/valdeira/ef-vfl","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"vertical-federated-learning","task_name":"Vertical Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.14420","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.14420"}},"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/valdeira/ef-vfl","reach":null}],"summary":{"ran_draft_wrong":2,"ran_honours":1,"unverified":1},"by_repo_kind":{"official":{"samples":4,"ran":3,"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":"01ae9fc577d07162","entry":"fetch_run_data","repo":"valdeira/ef-vfl","repo_kind":"official","path":"results/plot.py","file_url":"https://github.com/valdeira/ef-vfl/blob/HEAD/results/plot.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"01ae9fc577d07162"}},{"code_sha256_prefix":"5353c2fe665e3263","entry":"fetch_run_data","repo":"valdeira/ef-vfl","repo_kind":"official","path":"results/get_test_metrics.py","file_url":"https://github.com/valdeira/ef-vfl/blob/HEAD/results/get_test_metrics.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"5353c2fe665e3263"}},{"code_sha256_prefix":"582b3ef62e733c0a","entry":"group_runs_by_base_name","repo":"valdeira/ef-vfl","repo_kind":"official","path":"results/plot.py","file_url":"https://github.com/valdeira/ef-vfl/blob/HEAD/results/plot.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":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"582b3ef62e733c0a"}},{"code_sha256_prefix":"e889baa66d22001b","entry":"group_runs_by_base_name","repo":"valdeira/ef-vfl","repo_kind":"official","path":"results/get_test_metrics.py","file_url":"https://github.com/valdeira/ef-vfl/blob/HEAD/results/get_test_metrics.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":"e889baa66d22001b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}