{"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/data-free-knowledge-distillation-for-1","title":"Data-Free Knowledge Distillation for Heterogeneous Federated Learning","arxiv_id":"2105.10056","date":"2021-05-20","proceeding":null,"authors":["Zhuangdi Zhu","Junyuan Hong","Jiayu Zhou"],"abstract":"Federated Learning (FL) is a decentralized machine-learning paradigm, in which a global server iteratively averages the model parameters of local users without accessing their data. User heterogeneity has imposed significant challenges to FL, which can incur drifted global models that are slow to converge. Knowledge Distillation has recently emerged to tackle this issue, by refining the server model using aggregated knowledge from heterogeneous users, other than directly averaging their model parameters. This approach, however, depends on a proxy dataset, making it impractical unless such a prerequisite is satisfied. Moreover, the ensemble knowledge is not fully utilized to guide local model learning, which may in turn affect the quality of the aggregated model. Inspired by the prior art, we propose a data-free knowledge distillation} approach to address heterogeneous FL, where the server learns a lightweight generator to ensemble user information in a data-free manner, which is then broadcasted to users, regulating local training using the learned knowledge as an inductive bias. Empirical studies powered by theoretical implications show that, our approach facilitates FL with better generalization performance using fewer communication rounds, compared with the state-of-the-art.","url_abs":"https://arxiv.org/abs/2105.10056v2","url_pdf":"https://arxiv.org/pdf/2105.10056v2.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":"data-free-knowledge-distillation-for-1","repo_url":"https://github.com/zhuangdizhu/FedGen","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"data-free-knowledge-distillation-for-1","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"}},{"paper_slug":"data-free-knowledge-distillation-for-1","repo_url":"https://github.com/TsingZ0/GFL","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"data-free-knowledge-distillation-for-1","repo_url":"https://github.com/TsingZ0/PFL-Non-IID","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"data-free-knowledge-distillation","task_name":"Data-free Knowledge Distillation"},{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"inductive-bias","task_name":"Inductive Bias"},{"task_slug":"knowledge-distillation","task_name":"Knowledge Distillation"}],"methods":[{"method_slug":"knowledge-distillation","method_name":"Knowledge Distillation"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2105.10056","atlas_url":"https://app.syntology.ai/?focus=2105.10056","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":"2105.10056"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2105.10056\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2105.10056"},"call":"get_concepts_for_paper(arxiv_id=\"2105.10056\")"}],"by_repo":[{"repo":"zhuangdizhu/FedGen","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1602.05629","1812.06127"],"harvested_for_calls":[{"arxiv_id":"1602.05629","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1602.05629"},"call":"get_harvested_code_for_paper(arxiv_id=\"1602.05629\")"},{"arxiv_id":"1812.06127","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1812.06127"},"call":"get_harvested_code_for_paper(arxiv_id=\"1812.06127\")"}]},{"repo":"KarhouTam/FL-bench","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"TsingZ0/GFL","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2209.10083"],"harvested_for_calls":[{"arxiv_id":"2209.10083","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2209.10083"},"call":"get_harvested_code_for_paper(arxiv_id=\"2209.10083\")"}]},{"repo":"TsingZ0/PFL-Non-IID","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":11,"harvested_for":["1602.05629","2001.01523","2012.04221","2012.08565","2102.07623","2106.03097","2106.06042","2107.00778","2111.04263","2306.11867","2308.10279"],"harvested_for_calls":[{"arxiv_id":"1602.05629","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"1602.05629"},"call":"get_harvested_code_for_paper(arxiv_id=\"1602.05629\")"},{"arxiv_id":"2001.01523","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2001.01523"},"call":"get_harvested_code_for_paper(arxiv_id=\"2001.01523\")"},{"arxiv_id":"2012.04221","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2012.04221"},"call":"get_harvested_code_for_paper(arxiv_id=\"2012.04221\")"},{"arxiv_id":"2012.08565","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2012.08565"},"call":"get_harvested_code_for_paper(arxiv_id=\"2012.08565\")"},{"arxiv_id":"2102.07623","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2102.07623"},"call":"get_harvested_code_for_paper(arxiv_id=\"2102.07623\")"},{"arxiv_id":"2106.03097","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.03097"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.03097\")"},{"arxiv_id":"2106.06042","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2106.06042"},"call":"get_harvested_code_for_paper(arxiv_id=\"2106.06042\")"},{"arxiv_id":"2107.00778","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2107.00778"},"call":"get_harvested_code_for_paper(arxiv_id=\"2107.00778\")"},{"arxiv_id":"2111.04263","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2111.04263"},"call":"get_harvested_code_for_paper(arxiv_id=\"2111.04263\")"},{"arxiv_id":"2306.11867","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2306.11867"},"call":"get_harvested_code_for_paper(arxiv_id=\"2306.11867\")"},{"arxiv_id":"2308.10279","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2308.10279"},"call":"get_harvested_code_for_paper(arxiv_id=\"2308.10279\")"}]}],"by_repo_harvested_for_is":"harvested_for: the arXiv ids (as Syntology's graph holds them) of every paper whose samples Syntology's graph links to this repository, in arXiv-id order, complete; the page names the first 3 and says how many more. A link only: it does not say the papers are the same work, that one copied the other, or that the code implements this paper's method; harvested_for_calls gives the get_harvested_code_for_paper call for each arXiv-shaped id among them","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":"7a00aea6259fc4a132a5921fd1c822c9569e46312653915efae33ebbd80793ed","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}