{"url":"/task/personalized-federated-learning","name":"Personalized Federated Learning","slug":"personalized-federated-learning","description_markdown":"The federated learning setup presents numerous challenges including data heterogeneity (differences in data distribution), device heterogeneity (in terms of computation capabilities, network connection, etc.), and communication efficiency.\r\nEspecially data heterogeneity makes it hard to learn a single shared global model that applies to all clients. To overcome these issues, Personalized Federated Learning (PFL) aims to personalize the global model for each client in the federation.","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":311,"papers_with_code":117,"benchmarks":7,"benchmark_tables_in_archive":7,"benchmark_tables_shown":7,"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":5,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/personalized-federated-learning-on-cifar-10","slug":"personalized-federated-learning-on-cifar-10","dataset":"CIFAR-10","dataset_url":"/dataset/cifar-10","rows_in_archive":7,"metrics":["ACC@1-10Clients","ACC@1-50Clients","ACC@1-100Clients","ACC@1-500Clients"],"first_row_in_archive_order":{"model":"pFedHN-PC","paper_title":"Personalized Federated Learning using Hypernetworks","paper_url":"/paper/personalized-federated-learning-using","paper_date":"2021-03-08","arxiv_id":"2103.04628","code_links":[{"title":"KarhouTam/FL-bench","url":"https://github.com/KarhouTam/FL-bench"},{"title":"AvivSham/pFedHN","url":"https://github.com/AvivSham/pFedHN"}],"syntology":null}},{"leaderboard":"/sota/personalized-federated-learning-on-cifar-100","slug":"personalized-federated-learning-on-cifar-100","dataset":"CIFAR-100","dataset_url":"/dataset/cifar-100","rows_in_archive":7,"metrics":["ACC@1-500","ACC@1-100Clients","ACC@1-50Clients","ACC@1-10Clients","ACC@5-100Clients"],"first_row_in_archive_order":{"model":"pFedGP-IP-data","paper_title":"Personalized Federated Learning with Gaussian Processes","paper_url":"/paper/personalized-federated-learning-with-gaussian","paper_date":"2021-06-29","arxiv_id":"2106.15482","code_links":[{"title":"IdanAchituve/pFedGP","url":"https://github.com/IdanAchituve/pFedGP"}],"syntology":null}},{"leaderboard":"/sota/personalized-federated-learning-on","slug":"personalized-federated-learning-on","dataset":"Shakespeare","dataset_url":null,"rows_in_archive":2,"metrics":["Acc@1","Acc@5"],"first_row_in_archive_order":{"model":"SuPerFed-MM","paper_title":"Connecting Low-Loss Subspace for Personalized Federated Learning","paper_url":"/paper/subspace-learning-for-personalized-federated","paper_date":"2021-09-16","arxiv_id":"2109.07628","code_links":[{"title":"vaseline555/superfed","url":"https://github.com/vaseline555/superfed"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}},{"leaderboard":"/sota/personalized-federated-learning-on-femnist","slug":"personalized-federated-learning-on-femnist","dataset":"FEMNIST","dataset_url":"/dataset/femnist","rows_in_archive":2,"metrics":["Acc@1","Acc@5"],"first_row_in_archive_order":{"model":"SuPerFed-MM","paper_title":"Connecting Low-Loss Subspace for Personalized Federated Learning","paper_url":"/paper/subspace-learning-for-personalized-federated","paper_date":"2021-09-16","arxiv_id":"2109.07628","code_links":[{"title":"vaseline555/superfed","url":"https://github.com/vaseline555/superfed"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}},{"leaderboard":"/sota/personalized-federated-learning-on-mnist-1","slug":"personalized-federated-learning-on-mnist-1","dataset":"MNIST","dataset_url":"/dataset/mnist","rows_in_archive":2,"metrics":["ACC@1-50Clients","ACC@1-100Clients","ACC@1-500Clients"],"first_row_in_archive_order":{"model":"SuPerFed-LM","paper_title":"Connecting Low-Loss Subspace for Personalized Federated Learning","paper_url":"/paper/subspace-learning-for-personalized-federated","paper_date":"2021-09-16","arxiv_id":"2109.07628","code_links":[{"title":"vaseline555/superfed","url":"https://github.com/vaseline555/superfed"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}},{"leaderboard":"/sota/personalized-federated-learning-on-omniglot","slug":"personalized-federated-learning-on-omniglot","dataset":"Omniglot","dataset_url":null,"rows_in_archive":2,"metrics":["ACC@1-50Clients"],"first_row_in_archive_order":{"model":"pFedHN-PC","paper_title":"Personalized Federated Learning using Hypernetworks","paper_url":"/paper/personalized-federated-learning-using","paper_date":"2021-03-08","arxiv_id":"2103.04628","code_links":[{"title":"KarhouTam/FL-bench","url":"https://github.com/KarhouTam/FL-bench"},{"title":"AvivSham/pFedHN","url":"https://github.com/AvivSham/pFedHN"}],"syntology":null}},{"leaderboard":"/sota/personalized-federated-learning-on-tiny","slug":"personalized-federated-learning-on-tiny","dataset":"Tiny ImageNet","dataset_url":"/dataset/tiny-imagenet","rows_in_archive":2,"metrics":["ACC@5-200Clients"],"first_row_in_archive_order":{"model":"SuPerFed-MM","paper_title":"Connecting Low-Loss Subspace for Personalized Federated Learning","paper_url":"/paper/subspace-learning-for-personalized-federated","paper_date":"2021-09-16","arxiv_id":"2109.07628","code_links":[{"title":"vaseline555/superfed","url":"https://github.com/vaseline555/superfed"}],"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}}}],"datasets":[{"url":"/dataset/cifar-10","name":"CIFAR-10","full_name":"CIFAR-10","num_papers_in_archive":16145},{"url":"/dataset/cifar-100","name":"CIFAR-100","full_name":"","num_papers_in_archive":9045},{"url":"/dataset/mnist","name":"MNIST","full_name":"","num_papers_in_archive":7651},{"url":"/dataset/tiny-imagenet","name":"Tiny ImageNet","full_name":"Tiny ImageNet","num_papers_in_archive":1232},{"url":"/dataset/femnist","name":"FEMNIST","full_name":"Federated Extended MNIST","num_papers_in_archive":16}],"subtasks":[],"parent_tasks":[{"url":"/task/federated-learning","name":"Federated Learning"}],"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":117,"tagged_in_all":311,"items":[{"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/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/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/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/federated-multi-task-learning-for-competing","title":"Ditto: Fair and Robust Federated Learning Through Personalization","date":"2020-12-08","arxiv_id":"2012.04221","repositories_listed":4,"syntology":{"n":18,"n_ran":15,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/personalized-federated-learning-with-moreau","title":"Personalized Federated Learning with Moreau Envelopes","date":"2020-06-16","arxiv_id":"2006.08848","repositories_listed":4,"syntology":null},{"url":"/paper/fedala-adaptive-local-aggregation-for","title":"FedALA: Adaptive Local Aggregation for Personalized Federated Learning","date":"2022-12-02","arxiv_id":"2212.01197","repositories_listed":3,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/on-bridging-generic-and-personalized","title":"On Bridging Generic and Personalized Federated Learning for Image Classification","date":"2021-07-02","arxiv_id":"2107.00778","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/exploiting-shared-representations-for","title":"Exploiting Shared Representations for Personalized Federated Learning","date":"2021-02-14","arxiv_id":"2102.07078","repositories_listed":3,"syntology":null},{"url":"/paper/personalized-federated-learning-with-first-1","title":"Personalized Federated Learning with First Order Model Optimization","date":"2020-12-15","arxiv_id":"2012.08565","repositories_listed":3,"syntology":{"n":2,"n_ran":1,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/personalized-federated-learning-via-feature","title":"Personalized Federated Learning via Feature Distribution Adaptation","date":"2024-11-01","arxiv_id":"2411.00329","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/low-resource-machine-translation-through-the","title":"Low-Resource Machine Translation through the Lens of Personalized Federated Learning","date":"2024-06-18","arxiv_id":"2406.12564","repositories_listed":2,"syntology":null},{"url":"/paper/federated-representation-learning-in-the","title":"Federated Representation Learning in the Under-Parameterized Regime","date":"2024-06-07","arxiv_id":"2406.04596","repositories_listed":2,"syntology":{"n":8,"n_ran":6,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/fedas-bridging-inconsistency-in-personalized","title":"FedAS: Bridging Inconsistency in Personalized Federated Learning","date":"2024-01-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pefll-a-lifelong-learning-approach-to","title":"PeFLL: Personalized Federated Learning by Learning to Learn","date":"2023-06-08","arxiv_id":"2306.05515","repositories_listed":2,"syntology":null},{"url":"/paper/efficient-personalized-federated-learning-via","title":"Efficient Personalized Federated Learning via Sparse Model-Adaptation","date":"2023-05-04","arxiv_id":"2305.02776","repositories_listed":2,"syntology":{"n":6,"n_ran":5,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/motley-benchmarking-heterogeneity-and","title":"Motley: Benchmarking Heterogeneity and Personalization in Federated Learning","date":"2022-06-18","arxiv_id":"2206.09262","repositories_listed":2,"syntology":null},{"url":"/paper/personalized-federated-learning-through-local","title":"Personalized Federated Learning through Local Memorization","date":"2021-11-17","arxiv_id":"2111.09360","repositories_listed":2,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":2}},{"url":"/paper/personalized-federated-learning-using","title":"Personalized Federated Learning using Hypernetworks","date":"2021-03-08","arxiv_id":"2103.04628","repositories_listed":2,"syntology":null},{"url":"/paper/fedu-a-unified-framework-for-federated-multi","title":"A New Look and Convergence Rate of Federated Multi-Task Learning with Laplacian Regularization","date":"2021-02-14","arxiv_id":"2102.07148","repositories_listed":2,"syntology":null},{"url":"/paper/personalized-federated-learning-with","title":"Personalized Federated Learning with Theoretical Guarantees: A Model-Agnostic Meta-Learning Approach","date":"2020-12-01","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/pfedmma-personalized-federated-fine-tuning","title":"pFedMMA: Personalized Federated Fine-Tuning with Multi-Modal Adapter for Vision-Language Models","date":"2025-07-07","arxiv_id":"2507.05394","repositories_listed":1,"syntology":{"n":11,"n_ran":1,"n_unverified":10,"n_pointer_only":11}},{"url":"/paper/dual-detector-re-optimization-for-federated","title":"Dual‑detector Re‑optimization for Federated Weakly Supervised Video Anomaly Detection Via Adaptive Dynamic Recursive Mapping","date":"2025-06-13","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fhbench-towards-efficient-and-personalized","title":"FHBench: Towards Efficient and Personalized Federated Learning for Multimodal Healthcare","date":"2025-04-15","arxiv_id":"2504.10817","repositories_listed":1,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/btfl-a-bayesian-based-test-time","title":"BTFL: A Bayesian-based Test-Time Generalization Method for Internal and External Data Distributions in Federated learning","date":"2025-03-09","arxiv_id":"2503.06633","repositories_listed":1,"syntology":null},{"url":"/paper/pm-moe-mixture-of-experts-on-private-model","title":"PM-MOE: Mixture of Experts on Private Model Parameters for Personalized Federated Learning","date":"2025-02-01","arxiv_id":"2502.00354","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/calibre-towards-fair-and-accurate","title":"Calibre: Towards Fair and Accurate Personalized Federated Learning with Self-Supervised Learning","date":"2024-12-28","arxiv_id":"2412.20020","repositories_listed":1,"syntology":null},{"url":"/paper/temporal-causal-discovery-in-dynamic-bayesian","title":"Federated Learning of Dynamic Bayesian Network via Continuous Optimization from Time Series Data","date":"2024-12-13","arxiv_id":"2412.09814","repositories_listed":1,"syntology":null}],"syntology_records":17,"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"}}