{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/personalized-federated-learning-using","title":"Personalized Federated Learning using Hypernetworks","arxiv_id":"2103.04628","date":"2021-03-08","proceeding":null,"authors":["Aviv Shamsian","Aviv Navon","Ethan Fetaya","Gal Chechik"],"abstract":"Personalized federated learning is tasked with training machine learning models for multiple clients, each with its own data distribution. The goal is to train personalized models in a collaborative way while accounting for data disparities across clients and reducing communication costs. We propose a novel approach to this problem using hypernetworks, termed pFedHN for personalized Federated HyperNetworks. In this approach, a central hypernetwork model is trained to generate a set of models, one model for each client. This architecture provides effective parameter sharing across clients, while maintaining the capacity to generate unique and diverse personal models. Furthermore, since hypernetwork parameters are never transmitted, this approach decouples the communication cost from the trainable model size. We test pFedHN empirically in several personalized federated learning challenges and find that it outperforms previous methods. Finally, since hypernetworks share information across clients we show that pFedHN can generalize better to new clients whose distributions differ from any client observed during training.","url_abs":"https://arxiv.org/abs/2103.04628v1","url_pdf":"https://arxiv.org/pdf/2103.04628v1.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":"personalized-federated-learning-using","repo_url":"https://github.com/AvivSham/pFedHN","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"unanswered"}},{"paper_slug":"personalized-federated-learning-using","repo_url":"https://github.com/KarhouTam/FL-bench","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"GPL-3.0"}}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"personalized-federated-learning","task_name":"Personalized Federated Learning"}],"methods":[{"method_slug":"hypernetwork","method_name":"HyperNetwork"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/personalized-federated-learning-on-cifar-10","task":"Personalized Federated Learning","dataset":"CIFAR-10","model":"pFedHN-PC","rank_in_archive_order":1,"of":7,"metrics":{"ACC@1-100Clients":"88.09","ACC@1-10Clients":"92.47","ACC@1-500Clients":"83.2","ACC@1-50Clients":"90.08"},"uses_additional_data":false},{"leaderboard":"/sota/personalized-federated-learning-on-cifar-10","task":"Personalized Federated Learning","dataset":"CIFAR-10","model":"pFedHN","rank_in_archive_order":2,"of":7,"metrics":{"ACC@1-100Clients":"87.97","ACC@1-10Clients":"90.83","ACC@1-50Clients":"88.38"},"uses_additional_data":false},{"leaderboard":"/sota/personalized-federated-learning-on-cifar-100","task":"Personalized Federated Learning","dataset":"CIFAR-100","model":"pFedHN-PC","rank_in_archive_order":4,"of":7,"metrics":{"ACC@1-100Clients":"52.40","ACC@1-10Clients":"68.15","ACC@1-500":"34.1","ACC@1-50Clients":"60.17"},"uses_additional_data":false},{"leaderboard":"/sota/personalized-federated-learning-on-cifar-100","task":"Personalized Federated Learning","dataset":"CIFAR-100","model":"pFedHN","rank_in_archive_order":5,"of":7,"metrics":{"ACC@1-100Clients":"53.24","ACC@1-10Clients":"65.74","ACC@1-50Clients":"59.46"},"uses_additional_data":false},{"leaderboard":"/sota/personalized-federated-learning-on-omniglot","task":"Personalized Federated Learning","dataset":"Omniglot","model":"pFedHN-PC","rank_in_archive_order":1,"of":2,"metrics":{"ACC@1-50Clients":"81.89"},"uses_additional_data":false},{"leaderboard":"/sota/personalized-federated-learning-on-omniglot","task":"Personalized Federated Learning","dataset":"Omniglot","model":"pFedHN","rank_in_archive_order":2,"of":2,"metrics":{"ACC@1-50Clients":"72.03"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2103.04628","atlas_url":"https://app.syntology.ai/?focus=2103.04628","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2103.04628"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2103.04628\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2103.04628"},"call":"get_concepts_for_paper(arxiv_id=\"2103.04628\")"}],"by_repo":[{"repo":"AvivSham/pFedHN","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"KarhouTam/FL-bench","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"bd669f2fffa80ff3a9344e1dfcdea8031baf16d88f628fbbde06317407bfc3a1","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}