{"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/measuring-the-effects-of-non-identical-data","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","arxiv_id":"1909.06335","date":"2019-09-13","proceeding":null,"authors":["Tzu-Ming Harry Hsu","Hang Qi","Matthew Brown"],"abstract":"Federated Learning enables visual models to be trained in a privacy-preserving way using real-world data from mobile devices. Given their distributed nature, the statistics of the data across these devices is likely to differ significantly. In this work, we look at the effect such non-identical data distributions has on visual classification via Federated Learning. We propose a way to synthesize datasets with a continuous range of identicalness and provide performance measures for the Federated Averaging algorithm. We show that performance degrades as distributions differ more, and propose a mitigation strategy via server momentum. Experiments on CIFAR-10 demonstrate improved classification performance over a range of non-identicalness, with classification accuracy improved from 30.1% to 76.9% in the most skewed settings.","url_abs":"https://arxiv.org/abs/1909.06335v1","url_pdf":"https://arxiv.org/pdf/1909.06335v1.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":"measuring-the-effects-of-non-identical-data","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":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/WonJoon-Yun/Non-IID-Dataset-Generator-Direc-Delta","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok"}},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/kai-yue/predictive-coding-fl","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/maxencenoble/Differential-Privacy-for-Heterogeneous-Federated-Learning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/nliulab/fl-benchmark","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok"}},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/seyoungahn/JSAC_FedDif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/seyoungahn/feddif","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/vaseline555/Federated-Learning-in-PyTorch","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"measuring-the-effects-of-non-identical-data","repo_url":"https://github.com/vaseline555/superfed","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"federated-learning","task_name":"Federated Learning"},{"task_slug":"classification","task_name":"General Classification"},{"task_slug":"privacy-preserving","task_name":"Privacy Preserving"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/1909.06335","atlas_url":"https://app.syntology.ai/?focus=1909.06335","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":"1909.06335"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"1909.06335\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"1909.06335"},"call":"get_concepts_for_paper(arxiv_id=\"1909.06335\")"}],"by_repo":[{"repo":"KarhouTam/FL-bench","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"WonJoon-Yun/Non-IID-Dataset-Generator-Direc-Delta","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"kai-yue/predictive-coding-fl","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"maxencenoble/Differential-Privacy-for-Heterogeneous-Federated-Learning","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["1812.06127"],"harvested_for_calls":[{"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":"nliulab/fl-benchmark","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seyoungahn/JSAC_FedDif","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"seyoungahn/feddif","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0},{"repo":"vaseline555/Federated-Learning-in-PyTorch","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":1,"harvested_for":["2003.00295"],"harvested_for_calls":[{"arxiv_id":"2003.00295","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2003.00295"},"call":"get_harvested_code_for_paper(arxiv_id=\"2003.00295\")"}]},{"repo":"vaseline555/superfed","kind":"listed","samples":0,"ran":0,"instrument":0,"unverified":0,"harvested_for_other_papers":2,"harvested_for":["1602.05629","2109.07628"],"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":"2109.07628","tool":"get_harvested_code_for_paper","arguments":{"arxiv_id":"2109.07628"},"call":"get_harvested_code_for_paper(arxiv_id=\"2109.07628\")"}]}],"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":"d7b076bc796dc291b113bc0d84d7b21a8c4bdc936be98645bc5b4f90af23bfb7","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}