{"url":"/task/federated-learning","name":"Federated Learning","slug":"federated-learning","description_markdown":"**Federated Learning** is a machine learning approach that allows multiple devices or entities to collaboratively train a shared model without exchanging their data with each other. Instead of sending data to a central server for training, the model is trained locally on each device, and only the model updates are sent to the central server, where they are aggregated to improve the shared model. \r\n\r\nThis approach allows for privacy-preserving machine learning, as each device keeps its data locally and only shares the information needed to improve the model.","categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Methodology","url":"/area/methodology"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":6771,"papers_with_code":1815,"benchmarks":12,"benchmark_tables_in_archive":12,"benchmark_tables_shown":12,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":10,"subtasks":5,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/federated-learning-on-cityscapes","slug":"federated-learning-on-cityscapes","dataset":"Cityscapes heterogeneous","dataset_url":"/dataset/cityscapes","rows_in_archive":9,"metrics":["mIoU"],"first_row_in_archive_order":{"model":"SiloBN + ASAM","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-landmarks-user-160k","slug":"federated-learning-on-landmarks-user-160k","dataset":"Landmarks-User-160k","dataset_url":null,"rows_in_archive":6,"metrics":["Acc@1-1262Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-0-10","slug":"federated-learning-on-cifar-100-alpha-0-10","dataset":"CIFAR-100 (alpha=0, 10 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-0-20","slug":"federated-learning-on-cifar-100-alpha-0-20","dataset":"CIFAR-100 (alpha=0, 20 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-0-5","slug":"federated-learning-on-cifar-100-alpha-0-5","dataset":"CIFAR-100 (alpha=0, 5 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-0-5-10","slug":"federated-learning-on-cifar-100-alpha-0-5-10","dataset":"CIFAR-100 (alpha=0.5, 10 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-0-5-20","slug":"federated-learning-on-cifar-100-alpha-0-5-20","dataset":"CIFAR-100 (alpha=0.5, 20 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-0-5-5","slug":"federated-learning-on-cifar-100-alpha-0-5-5","dataset":"CIFAR-100 (alpha=0.5, 5 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM + SWA","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-1000-10","slug":"federated-learning-on-cifar-100-alpha-1000-10","dataset":"CIFAR-100 (alpha=1000, 10 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-1000-20","slug":"federated-learning-on-cifar-100-alpha-1000-20","dataset":"CIFAR-100 (alpha=1000, 20 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar-100-alpha-1000-5","slug":"federated-learning-on-cifar-100-alpha-1000-5","dataset":"CIFAR-100 (alpha=1000, 5 clients per round)","dataset_url":null,"rows_in_archive":5,"metrics":["ACC@1-100Clients"],"first_row_in_archive_order":{"model":"FedASAM","paper_title":"Improving Generalization in Federated Learning by Seeking Flat Minima","paper_url":"/paper/improving-generalization-in-federated","paper_date":"2022-03-22","arxiv_id":"2203.11834","code_links":[{"title":"debcaldarola/fedsam","url":"https://github.com/debcaldarola/fedsam"}],"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}}},{"leaderboard":"/sota/federated-learning-on-cifar100-alpha-0-3-10","slug":"federated-learning-on-cifar100-alpha-0-3-10","dataset":"CIFAR100 (alpha=0.3, 10 clients per round)","dataset_url":null,"rows_in_archive":1,"metrics":["Average Top-1 Accuracy"],"first_row_in_archive_order":{"model":"AdaBest","paper_title":"AdaBest: Minimizing Client Drift in Federated Learning via Adaptive Bias Estimation","paper_url":"/paper/minimizing-client-drift-in-federated-learning","paper_date":"2022-04-27","arxiv_id":"2204.13170","code_links":[{"title":"fedsim-dev/fedsim","url":"https://github.com/fedsim-dev/fedsim"}],"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}}}],"datasets":[{"url":"/dataset/cityscapes","name":"Cityscapes","full_name":"","num_papers_in_archive":3702},{"url":"/dataset/speech-commands","name":"Speech Commands","full_name":"Speech Commands","num_papers_in_archive":392},{"url":"/dataset/samsum-corpus","name":"SAMSum","full_name":"","num_papers_in_archive":145},{"url":"/dataset/smm4h","name":"SMM4H","full_name":"Social Media Mining for Health Shared Task","num_papers_in_archive":41},{"url":"/dataset/leaf-benchmark","name":"LEAF Benchmark","full_name":"","num_papers_in_archive":19},{"url":"/dataset/unimib-shar","name":"UniMiB SHAR","full_name":"","num_papers_in_archive":4},{"url":"/dataset/cc-19","name":"CC-19","full_name":null,"num_papers_in_archive":3},{"url":"/dataset/advfed","name":"adVFed","full_name":"Tencent Federated Advertising CVR Dataset","num_papers_in_archive":1},{"url":"/dataset/fedtadbench","name":"FedTADBench","full_name":"","num_papers_in_archive":1},{"url":"/dataset/street-dataset","name":"Street Dataset","full_name":"","num_papers_in_archive":1}],"subtasks":[{"url":"/task/collaborative-fairness","name":"Collaborative Fairness"},{"url":"/task/contribution-assessment","name":"Contribution Assessment"},{"url":"/task/model-posioning","name":"Model Posioning"},{"url":"/task/personalized-federated-learning","name":"Personalized Federated Learning"},{"url":"/task/vertical-federated-learning","name":"Vertical Federated Learning"}],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":1815,"tagged_in_all":6771,"items":[{"url":"/paper/communication-efficient-learning-of-deep","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","date":"2016-02-17","arxiv_id":"1602.05629","repositories_listed":41,"syntology":{"n":77,"n_ran":40,"n_unverified":37,"n_pointer_only":50}},{"url":"/paper/federated-optimization-for-heterogeneous","title":"Federated Optimization in Heterogeneous Networks","date":"2018-12-14","arxiv_id":"1812.06127","repositories_listed":22,"syntology":{"n":26,"n_ran":9,"n_unverified":17,"n_pointer_only":9}},{"url":"/paper/adaptive-personalized-federated-learning","title":"Adaptive Personalized Federated Learning","date":"2020-03-30","arxiv_id":"2003.13461","repositories_listed":11,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/advances-and-open-problems-in-federated","title":"Advances and Open Problems in Federated Learning","date":"2019-12-10","arxiv_id":"1912.04977","repositories_listed":9,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/measuring-the-effects-of-non-identical-data","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","date":"2019-09-13","arxiv_id":"1909.06335","repositories_listed":9,"syntology":null},{"url":"/paper/adaptive-federated-optimization","title":"Adaptive Federated Optimization","date":"2020-02-29","arxiv_id":"2003.00295","repositories_listed":8,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/scaffold-stochastic-controlled-averaging-for","title":"SCAFFOLD: Stochastic Controlled Averaging for Federated Learning","date":"2019-10-14","arxiv_id":"1910.06378","repositories_listed":8,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/inverting-gradients-how-easy-is-it-to-break","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","date":"2020-03-31","arxiv_id":"2003.14053","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/fedmd-heterogenous-federated-learning-via","title":"FedMD: Heterogenous Federated Learning via Model Distillation","date":"2019-10-08","arxiv_id":"1910.03581","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/towards-federated-learning-at-scale-system","title":"Towards Federated Learning at Scale: System Design","date":"2019-02-04","arxiv_id":"1902.01046","repositories_listed":7,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/agnostic-federated-learning","title":"Agnostic Federated Learning","date":"2019-02-01","arxiv_id":"1902.00146","repositories_listed":7,"syntology":{"n":10,"n_ran":3,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/leaf-a-benchmark-for-federated-settings","title":"LEAF: A Benchmark for Federated Settings","date":"2018-12-03","arxiv_id":"1812.01097","repositories_listed":7,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/pfllib-personalized-federated-learning","title":"PFLlib: A Beginner-Friendly and Comprehensive Personalized Federated Learning Library and Benchmark","date":"2023-12-08","arxiv_id":"2312.04992","repositories_listed":6,"syntology":{"n":7,"n_ran":6,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/model-contrastive-federated-learning","title":"Model-Contrastive Federated Learning","date":"2021-03-30","arxiv_id":"2103.16257","repositories_listed":6,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/federated-learning-for-mobile-keyboard","title":"Federated Learning for Mobile Keyboard Prediction","date":"2018-11-08","arxiv_id":"1811.03604","repositories_listed":6,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/differentially-private-federated-learning-a","title":"Differentially Private Federated Learning: A Client Level Perspective","date":"2017-12-20","arxiv_id":"1712.07557","repositories_listed":6,"syntology":null},{"url":"/paper/deep-gradient-compression-reducing-the","title":"Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training","date":"2017-12-05","arxiv_id":"1712.01887","repositories_listed":6,"syntology":null},{"url":"/paper/robust-federated-learning-with-noisy-and","title":"Robust Federated Learning With Noisy and Heterogeneous Clients","date":"2022-01-01","arxiv_id":null,"repositories_listed":5,"syntology":null},{"url":"/paper/federated-learning-based-on-dynamic-1","title":"Federated Learning Based on Dynamic Regularization","date":"2021-11-08","arxiv_id":"2111.04263","repositories_listed":5,"syntology":{"n":15,"n_ran":6,"n_unverified":9,"n_pointer_only":9}},{"url":"/paper/federated-multi-task-learning-under-a-mixture","title":"Federated Multi-Task Learning under a Mixture of Distributions","date":"2021-08-23","arxiv_id":"2108.10252","repositories_listed":5,"syntology":{"n":17,"n_ran":3,"n_unverified":14,"n_pointer_only":1}},{"url":"/paper/fedml-a-research-library-and-benchmark-for","title":"FedML: A Research Library and Benchmark for Federated Machine Learning","date":"2020-07-27","arxiv_id":"2007.13518","repositories_listed":5,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":1}},{"url":"/paper/federated-optimization-for-heterogeneous-1","title":"Federated Optimization for Heterogeneous Networks","date":"2019-05-16","arxiv_id":null,"repositories_listed":5,"syntology":null},{"url":"/paper/gpfl-simultaneously-learning-global-and","title":"GPFL: Simultaneously Learning Global and Personalized Feature Information for Personalized Federated Learning","date":"2023-08-20","arxiv_id":"2308.10279","repositories_listed":4,"syntology":{"n":17,"n_ran":9,"n_unverified":8,"n_pointer_only":7}},{"url":"/paper/fedcp-separating-feature-information-for","title":"FedCP: Separating Feature Information for Personalized Federated Learning via Conditional Policy","date":"2023-07-01","arxiv_id":"2307.01217","repositories_listed":4,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/personalized-federated-learning-with-feature","title":"Personalized Federated Learning with Feature Alignment and Classifier Collaboration","date":"2023-06-20","arxiv_id":"2306.11867","repositories_listed":4,"syntology":{"n":16,"n_ran":12,"n_unverified":4,"n_pointer_only":10}},{"url":"/paper/few-shot-model-agnostic-federated-learning","title":"Few-Shot Model Agnostic Federated Learning","date":"2022-10-10","arxiv_id":null,"repositories_listed":4,"syntology":null},{"url":"/paper/communication-efficient-hierarchical","title":"Communication-Efficient Hierarchical Federated Learning for IoT Heterogeneous Systems with Imbalanced Data","date":"2021-07-14","arxiv_id":"2107.06548","repositories_listed":4,"syntology":null},{"url":"/paper/data-free-knowledge-distillation-for-1","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","date":"2021-05-20","arxiv_id":"2105.10056","repositories_listed":4,"syntology":null},{"url":"/paper/fedproto-federated-prototype-learning-over","title":"FedProto: Federated Prototype Learning across Heterogeneous Clients","date":"2021-05-01","arxiv_id":"2105.00243","repositories_listed":4,"syntology":null},{"url":"/paper/robust-federated-learning-by-mixture-of","title":"Robust Federated Learning by Mixture of Experts","date":"2021-04-23","arxiv_id":"2104.11700","repositories_listed":4,"syntology":null}],"syntology_records":20,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}