Papers › Connecting Low-Loss Subspace for Personalized Federated Learning

Connecting Low-Loss Subspace for Personalized Federated Learning

16 Sep 2021arXiv:2109.07628archive 2025-07-28

Seok-Ju Hahn, Minwoo Jeong, Junghye Lee

Due to the curse of statistical heterogeneity across clients, adopting a personalized federated learning method has become an essential choice for the successful deployment of federated learning-based services. Among diverse branches of personalization techniques, a model mixture-based personalization method is preferred as each client has their own personalized model as a result of federated learning. It usually requires a local model and a federated model, but this approach is either limited to partial parameter exchange or requires additional local updates, each of which is helpless to novel clients and burdensome to the client's computational capacity. As the existence of a connected subspace containing diverse low-loss solutions between two or more independent deep networks has been discovered, we combined this interesting property with the model mixture-based personalized federated learning method for improved performance of personalization. We proposed SuPerFed, a personalized federated learning method that induces an explicit connection between the optima of the local and the federated model in weight space for boosting each other. Through extensive experiments on several benchmark datasets, we demonstrated that our method achieves consistent gains in both personalization performance and robustness to problematic scenarios possible in realistic services.

PaperPDFCodeCode 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 2 code samples harvested from 1 repository linked to this paper: 0 ran · 2 unverified.

By repository: official repository: 2 samples from 1 repository, 0 ran (0 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.

vaseline555/superfed officialmentioned in papermentioned on GitHubpytorchSyntology: 2 samples, 0 ran · 2 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.

Code Syntology ran Syntology

2 samples harvested: 0 ran · 2 unverified. 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.

2unverified

Licence: 2 of the 2 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 vaseline555/superfed. “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. “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.

vaseline555/superfed official repository 2 samples, 0 ran · 2 unverified
basic_evaluate src/algorithm.py unverified no licence file found · pointer only · 5469feaf295f1cc9 · report
superfed_evaluate src/algorithm.py unverified no licence file found · pointer only · fa05180c9d1ab382 · report

Tasks

Ensemble LearningFederated LearningPersonalized Federated Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Personalized Federated Learning CIFAR-10 SuPerFed-MM ACC@1-100Clients 93.25 #3 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 SuPerFed-MM ACC@1-500Clients 90.81 #3 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 SuPerFed-MM ACC@1-50Clients 94.05 #3 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 SuPerFed-LM ACC@1-100Clients 93.20 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 SuPerFed-LM ACC@1-500Clients 89.63 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-10 SuPerFed-LM ACC@1-50Clients 93.88 #4 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 SuPerFed-LM ACC@5-100Clients 62.50 #6 of 7 Archive leaderboard report
Personalized Federated Learning CIFAR-100 SuPerFed-MM ACC@5-100Clients 60.14 #7 of 7 Archive leaderboard report
Personalized Federated Learning FEMNIST SuPerFed-MM Acc@1 85.20 #1 of 2 Archive leaderboard report
Personalized Federated Learning FEMNIST SuPerFed-MM Acc@5 99.16 #1 of 2 Archive leaderboard report
Personalized Federated Learning FEMNIST SuPerFed-LM Acc@1 83.36 #2 of 2 Archive leaderboard report
Personalized Federated Learning FEMNIST SuPerFed-LM Acc@5 98.81 #2 of 2 Archive leaderboard report
Personalized Federated Learning MNIST SuPerFed-LM ACC@1-100Clients 99.31 #1 of 2 Archive leaderboard report
Personalized Federated Learning MNIST SuPerFed-LM ACC@1-500Clients 98.83 #1 of 2 Archive leaderboard report
Personalized Federated Learning MNIST SuPerFed-LM ACC@1-50Clients 99.48 #1 of 2 Archive leaderboard report
Personalized Federated Learning MNIST SuPerFed-MM ACC@1-100Clients 99.38 #2 of 2 Archive leaderboard report
Personalized Federated Learning MNIST SuPerFed-MM ACC@1-500Clients 99.24 #2 of 2 Archive leaderboard report
Personalized Federated Learning Shakespeare SuPerFed-MM Acc@1 54.52 #1 of 2 Archive leaderboard report
Personalized Federated Learning Shakespeare SuPerFed-MM Acc@5 84.27 #1 of 2 Archive leaderboard report
Personalized Federated Learning Shakespeare SuPerFed-LM Acc@1 54.52 #2 of 2 Archive leaderboard report
Personalized Federated Learning Shakespeare SuPerFed-LM Acc@5 83.97 #2 of 2 Archive leaderboard report
Personalized Federated Learning Tiny ImageNet SuPerFed-MM ACC@5-200Clients 50.07 #1 of 2 Archive leaderboard report
Personalized Federated Learning Tiny ImageNet SuPerFed-LM ACC@5-200Clients 49.29 #2 of 2 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Orthogonal RegularizationProximity 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