{"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/minimizing-client-drift-in-federated-learning","title":"AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation","arxiv_id":"2204.13170","date":"2022-04-27","proceeding":null,"authors":["Farshid Varno","Marzie Saghayi","Laya Rafiee Sevyeri","Sharut Gupta","Stan Matwin","Mohammad Havaei"],"abstract":"In Federated Learning (FL), a number of clients or devices collaborate to train a model without sharing their data. Models are optimized locally at each client and further communicated to a central hub for aggregation. While FL is an appealing decentralized training paradigm, heterogeneity among data from different clients can cause the local optimization to drift away from the global objective. In order to estimate and therefore remove this drift, variance reduction techniques have been incorporated into FL optimization recently. However, these approaches inaccurately estimate the clients' drift and ultimately fail to remove it properly. In this work, we propose an adaptive algorithm that accurately estimates drift across clients. In comparison to previous works, our approach necessitates less storage and communication bandwidth, as well as lower compute costs. Additionally, our proposed methodology induces stability by constraining the norm of estimates for client drift, making it more practical for large scale FL. Experimental findings demonstrate that the proposed algorithm converges significantly faster and achieves higher accuracy than the baselines across various FL benchmarks.","url_abs":"https://arxiv.org/abs/2204.13170v4","url_pdf":"https://arxiv.org/pdf/2204.13170v4.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":"minimizing-client-drift-in-federated-learning","repo_url":"https://github.com/fedsim-dev/fedsim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/federated-learning-on-cifar100-alpha-0-3-10","task":"Federated Learning","dataset":"CIFAR100 (alpha=0.3, 10 clients per round)","model":"AdaBest","rank_in_archive_order":1,"of":1,"metrics":{"Average Top-1 Accuracy":"56.2"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2204.13170","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2204.13170"}},"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/fedsim-dev/fedsim","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"listed":{"samples":8,"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":"80be16d191c0ad4e","entry":"apply_on_dict","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim/utils/dict_ops.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim/utils/dict_ops.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"80be16d191c0ad4e"}},{"code_sha256_prefix":"58c0bf63e2ddbd44","entry":"decode_margs","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim_cli/utils.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim_cli/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"58c0bf63e2ddbd44"}},{"code_sha256_prefix":"54264fda6cbab53b","entry":"get_from_module","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim/utils/import_utils.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim/utils/import_utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"54264fda6cbab53b"}},{"code_sha256_prefix":"d04382d1c4b70279","entry":"get_output_size","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim/models/utils.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim/models/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d04382d1c4b70279"}},{"code_sha256_prefix":"1bf7169a354cb416","entry":"parse_class_from_file","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim_cli/utils.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim_cli/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1bf7169a354cb416"}},{"code_sha256_prefix":"74963996d8900867","entry":"vector_to_named_parameters_like","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim/utils/convert_parameters.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim/utils/convert_parameters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"74963996d8900867"}},{"code_sha256_prefix":"14e4f93102251ddc","entry":"vector_to_parameters_like","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim/utils/convert_parameters.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim/utils/convert_parameters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"14e4f93102251ddc"}},{"code_sha256_prefix":"81fde0e6751c67a5","entry":"vectorize_module","repo":"fedsim-dev/fedsim","repo_kind":"listed","path":"fedsim/utils/convert_parameters.py","file_url":"https://github.com/fedsim-dev/fedsim/blob/HEAD/fedsim/utils/convert_parameters.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"81fde0e6751c67a5"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}