Papers › Federated Optimization in Heterogeneous Networks

Federated Optimization in Heterogeneous Networks

14 Dec 2018arXiv:1812.06127archive 2025-07-28

Tian Li, Anit Kumar Sahu, Manzil Zaheer, Maziar Sanjabi, Ameet Talwalkar, Virginia Smith

Federated Learning is a distributed learning paradigm with two key challenges that differentiate it from traditional distributed optimization: (1) significant variability in terms of the systems characteristics on each device in the network (systems heterogeneity), and (2) non-identically distributed data across the network (statistical heterogeneity). In this work, we introduce a framework, FedProx, to tackle heterogeneity in federated networks. FedProx can be viewed as a generalization and re-parametrization of FedAvg, the current state-of-the-art method for federated learning. While this re-parameterization makes only minor modifications to the method itself, these modifications have important ramifications both in theory and in practice. Theoretically, we provide convergence guarantees for our framework when learning over data from non-identical distributions (statistical heterogeneity), and while adhering to device-level systems constraints by allowing each participating device to perform a variable amount of work (systems heterogeneity). Practically, we demonstrate that FedProx allows for more robust convergence than FedAvg across a suite of realistic federated datasets. In particular, in highly heterogeneous settings, FedProx demonstrates significantly more stable and accurate convergence behavior relative to FedAvg---improving absolute test accuracy by 22% on average.

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 26 code samples harvested from 10 repositories linked to this paper: 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. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 10 samples from 1 repository, 8 ran (8 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 16 samples from 9 repositories, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed). 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 7 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

litian96/FedProx officialmentioned in papermentioned on GitHubtfMITSyntology: 10 samples, 8 ran (0 instrument-failed) · 2 unverified report
Koukyosyumei/AIJack mentioned on GitHubpytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
MLOPTPSU/FedTorch mentioned on GitHubpytorchSyntology: not harvested report
MLOPTPSU/TorchFed mentioned on GitHubpytorchGPL-2.0Syntology: not harvested report
MediaBrain-SJTU/FedLESAM mentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 unverified report
bdemo/pfedbred_public mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Personalized Federated Learning with Feature Alignment and Classifier Collaboration (arXiv:2306.11867; that paper's own run record: 12 ran (of which 5 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 4 where Syntology's instrument failed) · 4 unverified) and PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning (arXiv:2310.09183; that paper's own run record: 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) · 1 unverified; the one sample that ran constructed an object rather than computing a result); nothing checks that they implement this paper's method. report
carbonati/fl-zoo mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Communication-Efficient Learning of Deep Networks from Decentralized Data (arXiv:1602.05629; that paper's own run record: 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); nothing checks that they implement this paper's method. report
gaoliang13/feddc mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correction (arXiv:2203.11751; that paper's own run record: 0 ran · 2 unverified); nothing checks that they implement this paper's method. report
intel/openfl mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
jaemin-shin/fedbalancer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Communication-Efficient Learning of Deep Networks from Decentralized Data (arXiv:1602.05629; that paper's own run record: 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); nothing checks that they implement this paper's method. report
maxencenoble/Differential-Privacy-for-Heterogeneous-Federated-Learning mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
mohamad-m2/federated-learning mentioned on GitHubpytorchSyntology: not harvested report
morningD/GrouProx mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
nliulab/fl-benchmark mentioned on GitHubtfSyntology: not harvested report
omarfoq/fedem mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 0 ran · 2 unverified report
omarfoq/knn-per mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
securefederatedai/openfl mentioned on GitHubjaxApache-2.0Syntology: not harvested 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
woodenchild95/fl-simulator mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
yjlee22/FedShare mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Federated Learning with Non-IID Data (arXiv:1806.00582; that paper's own run record: 2 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; 1 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
zhuangdizhu/FedGen mentioned on GitHubpytorchSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
zshuai8/FedGMM_ICML2023 mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Personalized Federated Learning under Mixture of Distributions (arXiv:2305.01068; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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

26 samples harvested: 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. “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
13ran
11unverified

Licence: 9 of the 26 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 10 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. “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”. “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.

litian96/FedProx official repository 10 samples, 8 ran (0 instrument-failed) · 2 unverified
batch_data in 20 papers utils/model_utils.py ran MIT (permissive) · 04eb2c09a69cabcd · report fixture: signature data:dict/0/?, batch_size:int/0/int · returned tuple · level recorded 2026-09-25
letter_to_vec utils/language_utils.py ran · honoured contract fingerprinted MIT (permissive) · 9bc011aaf4c2fb8e · report fixture: signature letter:str/0/str · returned list · level recorded 2026-09-22
parse_log in 9 papers plot_fig2.py ran MIT (permissive) · 3d95adf387c731eb · report fixture: signature file_name:str/0/str · returned tuple · level recorded 2026-09-25
parse_log in 9 papers plot_final_e20.py ran MIT (permissive) · 5391ae7139f5e1e0 · report fixture: signature file_name:str/0/str · returned tuple · level recorded 2026-09-25
read_data in 132 papers flearn/utils/model_utils.py ran MIT (permissive) · a89afa036306a733 · report fixture: signature train_data_dir:str/0/str, test_data_dir:str/0/str · returned tuple · level recorded 2026-09-25
read_data in 132 papers utils/model_utils.py ran MIT (permissive) · dace4e03c5c252fe · report fixture: signature train_data_dir:str/0/str, test_data_dir:str/0/str · returned tuple · level recorded 2026-09-25
split_line utils/language_utils.py ran fingerprinted MIT (permissive) · e2b598f14cd058f3 · report fixture: signature line:str/0/str · returned list · level recorded 2026-09-25
word_to_indices in 5 papers utils/language_utils.py ran · honoured contract fingerprinted MIT (permissive) · e4cdde6a274b8fac · report fixture: signature word:str/0/str · returned list · level recorded 2026-09-22
graph_size utils/tf_utils.py unverified MIT (permissive) · 1040c34113873b16 · report
load_data in 700 papers utils/stats.py unverified MIT (permissive) · aba66b6a320cf6f7 · report
Koukyosyumei/AIJack community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
FedAVGAPI src/aijack/collaborative/fedprox/api.py ran Apache-2.0 (permissive) · 40b2aface22c3f65 · report fixture: returned NoneType · level recorded 2026-09-24
BaseFedAPI src/aijack/collaborative/fedprox/api.py unverified Apache-2.0 (permissive) · 526a4afa8230f908 · report
FedProxAPI src/aijack/collaborative/fedprox/api.py unverified Apache-2.0 (permissive) · cf20999d4c175f74 · report
MediaBrain-SJTU/FedLESAM community (archive-listed) 2 samples, 0 ran · 2 unverified
Client in 24 papers client/fedprox.py unverified no licence file found · pointer only · 13d5f640c099c234 · report
fedprox client/fedprox.py unverified no licence file found · pointer only · 49711512972b76af · report
intel/openfl community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
FedProxOptimizer openfl/utilities/optimizers/torch/fedprox.py ran Apache-2.0 (permissive) · 06dfd1885c7c4e75 · report fixture: returned FedProxOptimizer · level recorded 2026-09-22
maxencenoble/Differential-Privacy-for-Heterogeneous-Federated-Learning community (archive-listed) 1 sample, 0 ran · 1 unverified
FedLOptimizer flearn/optimizers/fedoptimizer.py unverified GPL-3.0 (copyleft) · pointer only · 0554ed92f151547b · report
morningD/GrouProx community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
PerturbedGradientDescent flearn/optimizer/pgd.py ran no licence file found · pointer only · bbe68818d3f2e89a · report fixture: returned PerturbedGradientDescent · level recorded 2026-09-22
omarfoq/fedem community (archive-listed) 2 samples, 0 ran · 2 unverified
Aggregator in 13 papers aggregator.py unverified Apache-2.0 (permissive) · 60422dff1153974f · report
CentralizedAggregator aggregator.py unverified Apache-2.0 (permissive) · fa609f7144eb64b8 · report
omarfoq/knn-per community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ProxSGD utils/optim.py ran Apache-2.0 (permissive) · 81f4645fc4657364 · report fixture: returned ProxSGD · level recorded 2026-09-22
woodenchild95/fl-simulator community (archive-listed) 1 sample, 0 ran · 1 unverified
fedprox client/fedprox.py unverified no licence file found · pointer only · dbc073f0b7427f38 · report
zhuangdizhu/FedGen community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
FedProxOptimizer FLAlgorithms/servers/serverFedProx.py ran no licence file found · pointer only · 7f652ac95bb4006c · report fixture: returned FedProxOptimizer · level recorded 2026-09-22
Server in 21 papers FLAlgorithms/servers/serverFedProx.py ran no licence file found · pointer only · 451d36a73c8babcf · report fixture: returned Server · level recorded 2026-09-22
UserFedProx FLAlgorithms/servers/serverFedProx.py ran no licence file found · pointer only · 3e6d6a9103a13d63 · report fixture: returned UserFedProx · level recorded 2026-09-22
FedProx FLAlgorithms/servers/serverFedProx.py unverified no licence file found · pointer only · 293cf8f7e5665e3a · report

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.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

9 sibling assemblies for FedProx (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for FedProx (graph method: FedProx). 3 bricks; 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) · 2 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 9 siblings

  1. fedprox entry · level 0 · unverified · dbc073f0b7427f38
  2. Client helper · level 0 · unverified · d921f3444b19cd1d
  3. Dataset helper · level 1 · ran · 763117dabc45a37d

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

one of 9 siblings

  1. CentralizedAggregator entry · level 0 · unverified · fa609f7144eb64b8
  2. Aggregator helper · level 0 · unverified · 60422dff1153974f

harvested Assembly for FedProx (graph method: FedProx). 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 9 siblings

  1. PerturbedGradientDescent entry · level 1 · ran · bbe68818d3f2e89a

harvested Assembly for FedProx (graph method: FedProx). 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 9 siblings

  1. ProxSGD entry · level 1 · ran · 81f4645fc4657364

harvested Assembly for FedProx (graph method: FedProx). 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 9 siblings

  1. FedProxOptimizer entry · level 1 · ran · 06dfd1885c7c4e75

harvested Assembly for FedProx (graph method: FedProx). 12 bricks; individually on a fixture: 10 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; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. FedProx entry · level 0 · unverified · 293cf8f7e5665e3a
  2. Server helper · level 1 · ran · 451d36a73c8babcf
  3. UserFedProx update_rule · level 1 · ran · 3e6d6a9103a13d63
  4. read_data helper · level 0 · unverified · 84a910b186221aee
  5. read_user_data helper · level 1 · ran · our draft was wrong · 42e1737bd4ec3392
  6. get_dataset_name helper · level 1 · ran · our draft was wrong · 363b0a1f2289036b
  7. get_log_path helper · level 1 · ran · our draft was wrong · 5c4ddcb24259e62c
  8. FedProxOptimizer update_rule · level 1 · ran · 7f652ac95bb4006c
  9. User helper · level 1 · ran · 7f0a553d7972e0f1
  10. get_data_dir helper · level 1 · ran · our draft was wrong · f494d00eb5149c70
  11. convert_data helper · level 1 · ran · our draft was wrong · 6f6629dd2979fc07
  12. pFedIBOptimizer helper · level 1 · ran · 01a2c86decde069b

harvested Assembly for FedProx (graph method: FedProx). 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.

one of 9 siblings

  1. FedProxAPI entry · level 0 · unverified · cf20999d4c175f74
  2. FedAVGAPI helper · level 1 · ran · 40b2aface22c3f65
  3. BaseFedAPI helper · level 0 · unverified · 526a4afa8230f908

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

one of 9 siblings

  1. fedprox entry · level 0 · unverified · 49711512972b76af
  2. Client helper · level 0 · unverified · 13d5f640c099c234

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

one of 9 siblings

  1. FedLOptimizer entry · level 0 · unverified · 0554ed92f151547b

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="1812.06127") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Distributed OptimizationFederated Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Introduced by this paper: Proximity Regularization

Proximity Regularization

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