Papers › Federated Multi-Task Learning under a Mixture of Distributions

Federated Multi-Task Learning under a Mixture of Distributions

23 Aug 2021NeurIPS 2021 12arXiv:2108.10252archive 2025-07-28

Othmane Marfoq, Giovanni Neglia, Aurélien Bellet, Laetitia Kameni, Richard Vidal

The increasing size of data generated by smartphones and IoT devices motivated the development of Federated Learning (FL), a framework for on-device collaborative training of machine learning models. First efforts in FL focused on learning a single global model with good average performance across clients, but the global model may be arbitrarily bad for a given client, due to the inherent heterogeneity of local data distributions. Federated multi-task learning (MTL) approaches can learn personalized models by formulating an opportune penalized optimization problem. The penalization term can capture complex relations among personalized models, but eschews clear statistical assumptions about local data distributions. In this work, we propose to study federated MTL under the flexible assumption that each local data distribution is a mixture of unknown underlying distributions. This assumption encompasses most of the existing personalized FL approaches and leads to federated EM-like algorithms for both client-server and fully decentralized settings. Moreover, it provides a principled way to serve personalized models to clients not seen at training time. The algorithms' convergence is analyzed through a novel federated surrogate optimization framework, which can be of general interest. Experimental results on FL benchmarks show that our approach provides models with higher accuracy and fairness than state-of-the-art methods.

PaperPDFConference PDFCodeCode Syntology ran

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 17 code samples: 16 from 2 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 17: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified. Where Syntology's instrument failed: 1 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: official repository: 14 samples from 1 repository, 9 ran (9 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 where Syntology's instrument failed); 1 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 1 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. 1 of the 12 samples that ran has no recorded date.

omarfoq/fedem officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 9 ran (0 instrument-failed) · 5 unverified report
KarhouTam/FL-bench mentioned on GitHubpytorchGPL-3.0Syntology: not harvested 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
tj-kim/pfeddef_v1 mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
yixinyang69/newfedem mentioned on GitHubpytorchSyntology: not harvested 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

17 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 1 violated, 9 with no contract checked; 2 where Syntology's instrument failed) · 5 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.

1ran · violated contract
1ran · our draft was wrong
1ran; the contract check could not run
9ran
5unverified

Licence: 1 of the 17 samples is 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 2 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 is 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”. “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.

omarfoq/fedem official repository 14 samples, 9 ran (0 instrument-failed) · 5 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
utils/metrics.py ran fingerprinted Apache-2.0 (permissive) · 1484765c5a875320 · report fixture: signature y_pred:Tensor/2/float, y:Tensor/1/int · returned Tensor · level recorded 2026-09-25
args_to_string utils/args.py ran Apache-2.0 (permissive) · 2aa9eaee30e6f00f · report fixture: signature args:Args/0/? · returned str · level recorded 2026-09-25
binary_accuracy in 13 papers utils/metrics.py ran fingerprinted Apache-2.0 (permissive) · d86b1b7917839f9d · report fixture: signature y_pred:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-25
compute_mixing_matrix utils/decentralized.py ran Apache-2.0 (permissive) · 063c0646ab2e0dd5 · report fixture: signature adjacency_matrix:ndarray/2/float · returned ndarray · level recorded 2026-09-26
get_communication_graph utils/decentralized.py ran Apache-2.0 (permissive) · 90e04d573188fcbd · report fixture: signature n:int/0/int, p:float/0/float, seed:int/0/int · returned Graph · level recorded 2026-09-25
get_lr_scheduler in 17 papers utils/optim.py ran Apache-2.0 (permissive) · 2581454f884675e8 · report fixture: signature optimizer:SGD/0/?, scheduler_name:str/0/str, n_rounds:NoneType/0/? · returned LambdaLR · level recorded 2026-09-25
get_mixing_matrix utils/decentralized.py ran Apache-2.0 (permissive) · b7accb5913464f4a · report fixture: signature n:int/0/int, p:float/0/float, seed:int/0/int · returned ndarray · level recorded 2026-09-25
mse in 78 papers
census: 5 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
utils/metrics.py ran fingerprinted Apache-2.0 (permissive) · e5d7e349519111ef · report fixture: signature y_pred:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-25
parse_args in 355 papers utils/args.py ran Apache-2.0 (permissive) · 214218b6675ec25e · report fixture: signature args_list:list/1/str · returned Namespace · level recorded 2026-09-25
get_mobilenet in 7 papers models.py unverified Apache-2.0 (permissive) · 9c1e58d7bca6b6c9 · report
get_optimizer in 228 papers utils/optim.py unverified Apache-2.0 (permissive) · 2131ebbda92151a1 · report
get_squeezenet models.py unverified Apache-2.0 (permissive) · 3a84a16cfdc372ba · report
get_vgg11 models.py unverified Apache-2.0 (permissive) · 2d5ef5672e97f155 · report
init_clients run_experiment.py unverified Apache-2.0 (permissive) · 825bbd029f466ff8 · report
tj-kim/pfeddef_v1 community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
cuda in 9 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
transfer_attacks/TA_utils.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 558fdb5c17a3a411 · report fixture: signature tensor:Tensor/2/float, is_cuda:bool/0/bool · returned Tensor · level recorded 2026-09-22
where in 9 papers transfer_attacks/TA_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · f5f8985f740c045e · report fixture: signature cond:Tensor/2/bool, x:Tensor/2/float, y:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Repository not located 1 sample, 1 ran (0 instrument-failed) · 0 unverified
1 sample is 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.
str2bool in 533 papers repository not located ran · violated contract licence of this copy not recorded · f017532fc389cbfe · report fixture: signature v:str/0/str · returned bool · level recorded, date not recorded

Tasks

FairnessFederated LearningMulti-Task LearningPersonalized Federated Learning

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