Papers › Communication-Efficient Learning of Deep Networks from Decentralized Data

Communication-Efficient Learning of Deep Networks from Decentralized Data

17 Feb 2016arXiv:1602.05629archive 2025-07-28

H. Brendan McMahan, Eider Moore, Daniel Ramage, Seth Hampson, Blaise Agüera y Arcas

Modern mobile devices have access to a wealth of data suitable for learning models, which in turn can greatly improve the user experience on the device. For example, language models can improve speech recognition and text entry, and image models can automatically select good photos. However, this rich data is often privacy sensitive, large in quantity, or both, which may preclude logging to the data center and training there using conventional approaches. We advocate an alternative that leaves the training data distributed on the mobile devices, and learns a shared model by aggregating locally-computed updates. We term this decentralized approach Federated Learning. We present a practical method for the federated learning of deep networks based on iterative model averaging, and conduct an extensive empirical evaluation, considering five different model architectures and four datasets. These experiments demonstrate the approach is robust to the unbalanced and non-IID data distributions that are a defining characteristic of this setting. Communication costs are the principal constraint, and we show a reduction in required communication rounds by 10-100x as compared to synchronized stochastic gradient descent.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 77 code samples: 74 from 20 repositories linked to this paper, 3 identical to code harvested from another paper's repository. Across all 77: 47 ran (of which 17 constructed an object rather than computing a result; 27 with no instrument failure: 2 honoured, 0 violated, 25 with no contract checked; 20 where Syntology's instrument failed) · 30 unverified. Where Syntology's instrument failed: 19 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 74 samples from 20 repositories, 44 ran (27 with no instrument failure; 17 where Syntology's instrument failed); 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 6 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

41 repositories listed; official and paper-mentioned ones first.

AshwinRJ/Federated-Learning-PyTorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Learning: Challenges, Methods, and Future Directions (arXiv:1908.07873; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
BRAIN-chain/FRAIN mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Learning: Challenges, Methods, and Future Directions (arXiv:1908.07873; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
ErickaBermudez/har-fl-simulation mentioned on GitHubSyntology: not harvested report
HongshengHu/SIAs-Beyond_MIAs_in_Federated_Learning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
Koukyosyumei/NAIST-FedML-Experiments mentioned on GitHubpytorchSyntology: not harvested report
Kylin824/AndroidFLServer mentioned on GitHubSyntology: not harvested report
Kylin824/AndroidFederatedLearningServer mentioned on GitHubSyntology: not harvested report
LeoSerena/MSThesis mentioned on GitHubpytorchSyntology: not harvested report
Lyhao0212/FedAvg mentioned on GitHubpytorchSyntology: not harvested report
TinfoilHat0/Defending-Against-Backdoors-with-Robust-Learning-Rate mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (1 instrument-failed) · 0 unverified report
TsingZ0/FL-IoT mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (2 instrument-failed) · 2 unverified report
TsingZ0/PFL-Non-IID mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
TsuchiyaYutaro/federated_learning_note mentioned on GitHubSyntology: not harvested report
adap/flower mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FedBN: Federated Learning on Non-IID Features via Local Batch Normalization (arXiv:2102.07623; that paper's own run record: 7 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
andrewkkan/fathom mentioned on GitHubjaxApache-2.0Syntology: not harvested report
carbonati/fl-zoo mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
flexible-fl/flex-nlp mentioned on GitHubAGPL-3.0Syntology: not harvested report
futabato/FutabatedLearning mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
google/fedjax mentioned on GitHubjaxApache-2.0Syntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
hongshenghu/source-inference-fl mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
intel/openfl mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Optimization in Heterogeneous Networks (arXiv:1812.06127; that paper's own run record: 15 ran (of which 6 constructed an object rather than computing a result; 15 with no instrument failure: 2 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
jaemin-shin/fedbalancer mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
jahanxb/flcode mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
khanhnguyen21006/fldocvqa mentioned on GitHubpytorchSyntology: not harvested report
krishnap25/trfa mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
michelle0924hhx/DiffPrivate_FedLearning mentioned on GitHubtfSyntology: 14 samples, 5 ran (1 instrument-failed) · 9 unverified report
mohamad-m2/federated-learning mentioned on GitHubpytorchSyntology: not harvested report
nadavlab/federatedbehrt mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
nliulab/fl-benchmark mentioned on GitHubtfSyntology: not harvested report
securefederatedai/openfl mentioned on GitHubjaxApache-2.0Syntology: not harvested report
siddarth-c/FedGMA mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
soumyaxyz/Privacy-Preserving-Federated-Learning mentioned on GitHubpytorchSyntology: not harvested report
thejungwon/gc-fed mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
vaseline555/Federated-Learning-in-PyTorch mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Adaptive Federated Optimization (arXiv:2003.00295; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
vaseline555/superfed mentioned on GitHubpytorchSyntology: 4 samples, 2 ran (1 instrument-failed) · 2 unverified report
yjlee22/FedShare mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
yuetan031/fedproto mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
zhuangdizhu/FedGen mentioned on GitHubpytorchSyntology: 16 samples, 12 ran (7 instrument-failed) · 4 unverified report
MindSpore-scientific/code-4 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for... (arXiv:2402.17152; that paper's own run record: 15 ran (of which 13 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 1 where Syntology's instrument failed) · 27 unverified); nothing checks that they implement this paper's method. report
mikudehuane/Federated-Averaging pytorchSyntology: not harvested report
willyfh/federated-learning-tensorflow tfSyntology: 1 sample, 0 ran · 1 unverified report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

77 samples harvested: 47 ran (of which 17 constructed an object rather than computing a result; 27 with no instrument failure: 2 honoured, 0 violated, 25 with no contract checked; 20 where Syntology's instrument failed) · 30 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
19ran · our draft was wrong
1ran; the contract check could not run
25ran
30unverified

Licence: 50 of the 77 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 20 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. 3 samples are listed last, in a group without a repository. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

HongshengHu/SIAs-Beyond_MIAs_in_Federated_Learning community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
FedAvg in 21 papers FedAvg-SIAs/models/Fed.py ran · our draft was wrong no licence file found · pointer only · 5719ee7d03438fcb · report fixture: signature w:list/1/dict, weight:list/1/float · returned dict · level recorded 2026-09-22
TinfoilHat0/Defending-Against-Backdoors-with-Robust-Learning-Rate community (archive-listed) 4 samples, 4 ran (1 instrument-failed) · 0 unverified
Aggregation src/aggregation.py ran MIT (permissive) · 27387c8ca3db36f7 · report fixture: returned Aggregation · level recorded 2026-09-22
CNN_CIFAR src/aggregation.py ran MIT (permissive) · 27acc6a286937512 · report fixture: returned CNN_CIFAR · level recorded 2026-09-22
CNN_MNIST src/aggregation.py ran MIT (permissive) · 90b6212457a2eeac · report fixture: returned CNN_MNIST · level recorded 2026-09-22
get_model in 368 papers src/aggregation.py ran · our draft was wrong MIT (permissive) · 4472f07d6a8fd2f2 · report fixture: signature data:str/0/str · returned CNN_CIFAR · level recorded 2026-09-22
TsingZ0/FL-IoT community (archive-listed) 4 samples, 2 ran (2 instrument-failed) · 2 unverified
read_client_data in 11 papers system/flcore/servers/serverbase.py ran · our draft was wrong MIT (permissive) · f417998fde6fd19a · report fixture: signature dataset:str/0/str, idx:int/0/int, is_train:bool/0/bool · returned list · level recorded 2026-09-22
read_client_data_text in 7 papers system/flcore/servers/serverbase.py ran · our draft was wrong MIT (permissive) · a5adfb5eb99305a0 · report fixture: signature dataset:str/0/str, idx:int/0/int, is_train:bool/0/bool · returned list · level recorded 2026-09-22
Server in 21 papers system/flcore/servers/serverbase.py unverified MIT (permissive) · 1ec6ded80631df99 · report
read_data in 132 papers system/flcore/servers/serverbase.py unverified MIT (permissive) · 1689826ac99c2f30 · report
TsingZ0/PFL-Non-IID community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Client in 24 papers system/flcore/servers/serveravg.py ran Apache-2.0 (permissive) · 94a806a7b827ab03 · report fixture: returned Client · level recorded 2026-09-22
DLG in 5 papers system/flcore/servers/serveravg.py ran · honoured contract Apache-2.0 (permissive) · 8bc43a565d54b3b7 · report fixture: signature net:callable/0/?, origin_grad:list/1/Tensor, target_inputs:list/1/tuple · returned float32 · level recorded 2026-09-22
clientAVG system/flcore/servers/serveravg.py ran Apache-2.0 (permissive) · 3bc02616a0c2f3c0 · report fixture: returned clientAVG · level recorded 2026-09-22
FedAvg in 21 papers system/flcore/servers/serveravg.py unverified Apache-2.0 (permissive) · 01b0d50f47833fc2 · report
Server in 21 papers system/flcore/servers/serveravg.py unverified Apache-2.0 (permissive) · 4a872374dd01c93c · report
carbonati/fl-zoo community (archive-listed) 2 samples, 0 ran · 2 unverified
BaseFederater fl_zoo/optimizers/fed_avg.py unverified no licence file found · pointer only · 3b5b02a898d9474a · report
FedAvg in 21 papers fl_zoo/optimizers/fed_avg.py unverified no licence file found · pointer only · ace0580d4c7a8494 · report
futabato/FutabatedLearning community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
average_weights in 13 papers src/federatedlearning/server/aggregations/aggregators.py ran · our draft was wrong MIT (permissive) · 0964f793bbd43856 · report fixture: signature local_weights:list/1/dict · returned dict · level recorded 2026-09-22
google/fedjax community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
concat_examples fedjax/core/client_datasets.py ran Apache-2.0 (permissive) · cb706aa8e56ba095 · report fixture: signature many_examples:list/1/dict · returned dict · level recorded 2026-09-26
f in 68 papers
census: 17 implementations from 15 papers, 17 distinct outputs across 7 buckets, one shared input per bucket
fedjax/core/client_datasets_benchmark.py ran Apache-2.0 (permissive) · dcee316376a55eb4 · report fixture: signature x:dict/0/? · returned dict · level recorded 2026-09-26
get_pseudo_random_state fedjax/core/client_samplers.py ran Apache-2.0 (permissive) · 3ee7d7048f08a521 · report fixture: signature seed:int/0/int, round_num:int/0/int · returned RandomState · level recorded 2026-09-26
interpolation_grad_fn fedjax/algorithms/apfl.py ran Apache-2.0 (permissive) · b30e159a1a359cb7 · report fixture: signature grads:dict/0/?, client_params:dict/0/?, server_params:dict/0/? · returned dict · level recorded 2026-09-26
num_examples fedjax/core/client_datasets.py ran Apache-2.0 (permissive) · 502c0dd72f65b76b · report fixture: signature examples:dict/0/?, validate:bool/0/bool · returned int · level recorded 2026-09-26
slice_examples fedjax/core/client_datasets.py ran Apache-2.0 (permissive) · a6e676db5d309765 · report fixture: signature examples:dict/0/?, index:slice/0/? · returned dict · level recorded 2026-09-26
dataclass in 5 papers fedjax/core/dataclasses.py unverified Apache-2.0 (permissive) · a36088e67fbe174c · report
interpolate_params fedjax/algorithms/apfl.py unverified Apache-2.0 (permissive) · 2602483010db71c1 · report
hongshenghu/source-inference-fl community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
FedAvg in 21 papers models/Fed.py ran · our draft was wrong no licence file found · pointer only · f9964d719c5cb8f4 · report fixture: signature w:list/1/dict · returned dict · level recorded 2026-09-22
jaemin-shin/fedbalancer community (archive-listed) 1 sample, 0 ran · 1 unverified
PerturbedGradientDescent models/fedprox.py unverified BSD-2-Clause (permissive) · 1bf34112ce4681b0 · report
jahanxb/flcode community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
aggregation_avg utils/aggregation.py ran · our draft was wrong no licence file found · pointer only · 149a5f07c19c3bc1 · report fixture: signature global_model:dict/0/?, local_updates:list/1/dict · returned dict · level recorded 2026-09-22
krishnap25/trfa community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
Server in 21 papers models/server.py ran BSD-2-Clause (permissive) · 97fedffecec3aab4 · report fixture: returned Server · level recorded 2026-09-22
michelle0924hhx/DiffPrivate_FedLearning community (archive-listed) 14 samples, 5 ran (1 instrument-failed) · 9 unverified
GaussianMomentsAccountant DiffPrivate_FedLearning.py ran no licence file found · pointer only · 3068c1c62cfc8856 · report fixture: returned GaussianMomentsAccountant · level recorded 2026-09-22
GenerateBinomialTable DiffPrivate_FedLearning.py ran · honoured contract fingerprinted no licence file found · pointer only · f80efcf932ec4fc9 · report fixture: signature m:int/0/int · returned EagerTensor · level recorded 2026-09-22
MomentsAccountant DiffPrivate_FedLearning.py ran no licence file found · pointer only · 3a4c930f37c98bb3 · report fixture: returned MomentsAccountant · level recorded 2026-09-22
PrivAgent DiffPrivate_FedLearning.py ran no licence file found · pointer only · b7721a7ba8bc78a8 · report fixture: returned PrivAgent · level recorded 2026-09-22
check_validaity_of_FLAGS DiffPrivate_FedLearning.py ran · our draft was wrong no licence file found · pointer only · 613879cfff5654f0 · report fixture: signature FLAGS:SimpleNamespace/0/? · returned SimpleNamespace · level recorded 2026-09-22
Flag DiffPrivate_FedLearning.py unverified no licence file found · pointer only · 4593abf3a327baff · report
WeightsAccountant DiffPrivate_FedLearning.py unverified no licence file found · pointer only · 93ea07af87ba7658 · report
bring_Accountant_up_to_date DiffPrivate_FedLearning.py unverified no licence file found · pointer only · a7f11a62bc15ac32 · report
global_step_creator DiffPrivate_FedLearning.py unverified no licence file found · pointer only · b39d33cd042fdb29 · report
load_from_directory_or_initialize DiffPrivate_FedLearning.py unverified no licence file found · pointer only · e3197a91e56e1d29 · report
print_loss_and_accuracy DiffPrivate_FedLearning.py unverified no licence file found · pointer only · 4ed5df8adc24ce03 · report
print_new_comm_round DiffPrivate_FedLearning.py unverified no licence file found · pointer only · 971f2e53c3ea8040 · report
run_differentially_private_federated_averaging DiffPrivate_FedLearning.py unverified no licence file found · pointer only · e5893d26b59ab8d7 · report
save_progress DiffPrivate_FedLearning.py unverified no licence file found · pointer only · 481ec0c09590a06c · report
nadavlab/federatedbehrt community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
launch_tensor_board src/utils.py ran Apache-2.0 (permissive) · a7ec603ffc6341e9 · report fixture: signature log_path:str/0/str, port:int/0/int, host:str/0/str · returned bool · level recorded 2026-09-26
init_net in 47 papers src/utils.py unverified Apache-2.0 (permissive) · 6e22953f199abc82 · report
siddarth-c/FedGMA community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
GenerateModels FedGMA.py ran no licence file found · pointer only · ba03b24a1c116ca5 · report fixture: returned tuple · level recorded 2026-09-22
FedGMA FedGMA.py unverified no licence file found · pointer only · d3598b24ac0de8b1 · report
MNISTtier FedGMA.py unverified no licence file found · pointer only · d741d8a02d52077a · report
thejungwon/gc-fed community (archive-listed) 2 samples, 0 ran · 2 unverified
FedAvg in 21 papers algorithms/fedavg.py unverified no licence file found · pointer only · 32845aa08d8061c2 · report
FedAvgClient algorithms/fedavg.py unverified no licence file found · pointer only · f23e66c3c788f6d3 · report
vaseline555/superfed community (archive-listed) 4 samples, 2 ran (1 instrument-failed) · 2 unverified
CalibrationError src/algorithm.py ran · metamorphic tier: deterministic no licence file found · pointer only · 30399e1931903438 · report fixture: returned CalibrationError · level recorded 2026-09-22
get_accuracy in 52 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
src/algorithm.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · a8ce655aa6965797 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned Tensor · level recorded 2026-09-22
basic_update src/algorithm.py unverified no licence file found · pointer only · e2fccae0b0de2c93 · report
initiate_model src/algorithm.py unverified no licence file found · pointer only · 11ed58b6be97110c · report
yjlee22/FedShare community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
FedAvg in 21 papers src/strategy.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 75d8463105db0e97 · report fixture: signature w:list/1/dict, args:Args/0/? · returned dict · level recorded 2026-09-22
yuetan031/fedproto community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
DatasetSplit in 7 papers lib/update.py ran no licence file found · pointer only · c78fddd166ce8803 · report fixture: returned DatasetSplit · level recorded 2026-09-22
LocalUpdate in 7 papers lib/update.py ran no licence file found · pointer only · cbaf694f21e1aee7 · report fixture: returned LocalUpdate · level recorded 2026-09-22
zhuangdizhu/FedGen community (archive-listed) 16 samples, 12 ran (7 instrument-failed) · 4 unverified
DiversityLoss FLAlgorithms/servers/serverpFedGen.py ran fingerprinted no licence file found · pointer only · 9002f2f24f643954 · report fixture: returned DiversityLoss · level recorded 2026-09-22
Generator in 95 papers FLAlgorithms/servers/serverpFedGen.py ran no licence file found · pointer only · 3bb64f6c7b4918a8 · report fixture: returned Generator · level recorded 2026-09-22
Server in 21 papers FLAlgorithms/servers/serverpFedGen.py ran no licence file found · pointer only · 1289a4420bf541e2 · report fixture: returned Server · level recorded 2026-09-22
User FLAlgorithms/servers/serverpFedGen.py ran no licence file found · pointer only · 7f0a553d7972e0f1 · report fixture: returned User · level recorded 2026-09-22
aggregate_data_ FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong no licence file found · pointer only · e1a5ca9193a358f7 · report fixture: signature clients:list/1/str, dataset:dict/0/?, dataset_name:str/0/str, batch_size:int/0/int · returned tuple · level recorded 2026-09-22
aggregate_user_data FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong no licence file found · pointer only · 7661927a759ac10e · report fixture: signature data:list/1/list, dataset_name:str/0/str, batch_size:int/0/int · returned tuple · level recorded 2026-09-22
convert_data FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 6f6629dd2979fc07 · report fixture: signature X:ndarray/2/float, y:ndarray/1/int, dataset:str/0/str · returned tuple · level recorded 2026-09-22
get_data_dir in 9 papers FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong no licence file found · pointer only · f494d00eb5149c70 · report fixture: signature dataset:str/0/str · returned tuple · level recorded 2026-09-22
get_dataset_name in 6 papers FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong no licence file found · pointer only · 363b0a1f2289036b · report fixture: signature dataset:str/0/str · returned str · level recorded 2026-09-22
get_log_path FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong no licence file found · pointer only · 5c4ddcb24259e62c · report fixture: signature args:Args/0/?, algorithm:str/0/str, seed:int/0/int, gen_batch_size:int/0/int · returned str · level recorded 2026-09-22
pFedIBOptimizer FLAlgorithms/servers/serverpFedGen.py ran no licence file found · pointer only · 01a2c86decde069b · report fixture: returned pFedIBOptimizer · level recorded 2026-09-22
read_user_data FLAlgorithms/servers/serverpFedGen.py ran · our draft was wrong no licence file found · pointer only · 42e1737bd4ec3392 · report fixture: signature index:int/0/int, data:list/1/list, dataset:str/0/str, count_labels:bool/0/bool · returned tuple · level recorded 2026-09-22
FedGen FLAlgorithms/servers/serverpFedGen.py unverified no licence file found · pointer only · 145ea8a36102e663 · report
UserpFedGen FLAlgorithms/servers/serverpFedGen.py unverified no licence file found · pointer only · 8e4739acd40f3d69 · report
create_generative_model FLAlgorithms/servers/serverpFedGen.py unverified no licence file found · pointer only · 64c46ba1e1f82f7e · report
read_data in 132 papers FLAlgorithms/servers/serverpFedGen.py unverified no licence file found · pointer only · 84a910b186221aee · report
willyfh/federated-learning-tensorflow community (archive-listed) 1 sample, 0 ran · 1 unverified
train in 522 papers federated_train.py unverified MIT (permissive) · f457743261fa931b · report
Repository not located 3 samples, 3 ran (3 instrument-failed) · 0 unverified
3 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
Vname_to_FeedPname repository not located ran · our draft was wrong licence of this copy not recorded · 4b5f34895003fc5f · report fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22
Vname_to_Pname repository not located ran · our draft was wrong licence of this copy not recorded · 96ac62e9e705aa09 · report fixture: signature var:MockVariable/0/? · returned str · level recorded 2026-09-22
create_save_dir in 7 papers repository not located ran · our draft was wrong licence of this copy not recorded · f466d758bb1dc678 · report fixture: signature FLAGS:FLAGS/0/? · returned str · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

18 assemblies on this paper: 18 harvested, 0 generated, listed in 2 groups (siblings lifted in one batch form one group).

17 sibling assemblies for Federated Learning (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 17 sibling assemblies; the other 5 are listed with their counts; every brick is in this page's JSON twin.

harvested Assembly for Federated Learning (graph method: Federated Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. FedAvg entry · level 1 · ran · our draft was wrong · f9964d719c5cb8f4

harvested Assembly for Federated Learning (graph method: Federated Learning). 1 brick; individually on a fixture: 1 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. Server entry · level 1 · ran · 97fedffecec3aab4

harvested Assembly for Federated Learning (graph method: Federated Learning). 2 bricks; individually on a fixture: 0 ran · 2 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. FedAvg entry · level 0 · unverified · ace0580d4c7a8494
  2. BaseFederater helper · level 0 · unverified · 3b5b02a898d9474a

harvested Assembly for Federated Learning (graph method: Federated Learning). 11 bricks; individually on a fixture: 8 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. FedAvg entry · level 0 · unverified · 01b0d50f47833fc2
  2. Server helper · level 0 · unverified · 4a872374dd01c93c
  3. clientAVG update_rule · level 1 · ran · 3bc02616a0c2f3c0
  4. DLG helper · level 1 · ran · honoured contract · 8bc43a565d54b3b7
  5. read_client_data helper · level 0 · unverified · ee5f6af39c3092db
  6. Client helper · level 1 · ran · 94a806a7b827ab03
  7. psnr helper · level 1 · ran · honoured contract · 417018913135e19a
  8. process_Shakespeare helper · level 1 · ran · our draft was wrong · 13727b959b74cb36
  9. process_image helper · level 1 · ran · our draft was wrong · eeaf321abdedfa1f
  10. process_text helper · level 1 · ran · our draft was wrong · bff598ba2b65008a
  11. read_data helper · level 1 · ran · honoured contract · 8eebe137489ff326

harvested Assembly for Federated Learning (graph method: Federated Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. FedAvg entry · level 1 · ran · our draft was wrong · 5719ee7d03438fcb

harvested Assembly for Federated Learning (graph method: Federated Learning). 2 bricks; individually on a fixture: 2 ran (of which 2 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. LocalUpdate entry · level 1 · ran · cbaf694f21e1aee7
  2. DatasetSplit helper · level 1 · ran · c78fddd166ce8803

harvested Assembly for Federated Learning (graph method: Federated Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. aggregation_avg entry · level 1 · ran · our draft was wrong · 149a5f07c19c3bc1

harvested Assembly for Federated Learning (graph method: Federated Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. average_weights entry · level 1 · ran · our draft was wrong · 0964f793bbd43856

harvested Assembly for Federated Learning (graph method: Federated Learning). 4 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. basic_update entry · level 0 · unverified · e2fccae0b0de2c93
  2. CalibrationError helper · level 1 · ran · 30399e1931903438
  3. get_accuracy helper · level 1 · ran; the contract check could not run (RAISES) · a8ce655aa6965797
  4. initiate_model helper · level 0 · unverified · 11ed58b6be97110c

harvested Assembly for Federated Learning (graph method: Federated Learning). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. FedAvg entry · level 1 · ran · our draft was wrong · 75d8463105db0e97

harvested Assembly for Federated Learning (graph method: Federated Learning). 17 bricks; individually on a fixture: 8 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 9 unverified. The assembly has not been run end-to-end.

one of 17 siblings

  1. run_differentially_private_federated_averaging entry · level 0 · unverified · e5893d26b59ab8d7
  2. Flag helper · level 0 · unverified · 4593abf3a327baff
  3. PrivAgent helper · level 1 · ran · b7721a7ba8bc78a8
  4. Vname_to_FeedPname helper · level 1 · ran · our draft was wrong · 4b5f34895003fc5f
  5. Vname_to_Pname helper · level 1 · ran · our draft was wrong · 96ac62e9e705aa09
  6. WeightsAccountant helper · level 0 · unverified · 93ea07af87ba7658
  7. bring_Accountant_up_to_date helper · level 0 · unverified · a7f11a62bc15ac32
  8. check_validaity_of_FLAGS helper · level 1 · ran · our draft was wrong · 613879cfff5654f0
  9. create_save_dir helper · level 1 · ran · our draft was wrong · f466d758bb1dc678
  10. global_step_creator helper · level 0 · unverified · b39d33cd042fdb29
  11. load_from_directory_or_initialize helper · level 0 · unverified · e3197a91e56e1d29
  12. print_loss_and_accuracy helper · level 0 · unverified · 4ed5df8adc24ce03
  13. print_new_comm_round helper · level 0 · unverified · 971f2e53c3ea8040
  14. save_progress helper · level 0 · unverified · 481ec0c09590a06c
  15. GaussianMomentsAccountant helper · level 1 · ran · 3068c1c62cfc8856
  16. GenerateBinomialTable helper · level 1 · ran · honoured contract · f80efcf932ec4fc9
  17. MomentsAccountant helper · level 1 · ran · 3a4c930f37c98bb3

harvested Assembly for Federated Learning (graph method: Federated Learning). 11 bricks; individually on a fixture: 4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified; every one of the 4 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 17 siblings

  1. FedAvg entry · level 0 · unverified · 32845aa08d8061c2
  2. FedAvgClient helper · level 0 · unverified · f23e66c3c788f6d3
  3. evaluate helper · level 0 · unverified · 1a0a0b3bfb388c6e
  4. get_model helper · level 0 · unverified · 021173b9b0b6da38
  5. log_info helper · level 0 · unverified · a2a34e406dfeba02
  6. set_random_seed helper · level 0 · unverified · 55dd9a2df5092e25
  7. CNN helper · level 1 · ran · cff80b8ecb8c8c99
  8. MLP helper · level 1 · ran · acd09ebeda2c9bc6
  9. ResNet18 helper · level 1 · ran · ce17439507a51476
  10. VGG11 helper · level 1 · ran · f0aeb868a782b3d7
  11. init_weights helper · level 0 · unverified · 39c6548f5ca70964
  1. FedGen · 8c48ab19a17c0fc6 · 16 bricks; individually on a fixture: 12 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 4 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
  2. train · 9905e367bce9bc63 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
  3. Aggregation · 9bed5023a0c41d3d · 4 bricks; individually on a fixture: 4 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
  4. Server · a5fd2feb7ecfacd9 · 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
  5. FedGMA · bc28b5be074a2b52 · 3 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin

harvested Assembly for Federated Learning (graph method: FedProx). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. PerturbedGradientDescent entry · level 0 · unverified · 1bf34112ce4681b0

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1602.05629") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Federated LearningSpeech Recognition

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections