Papers › FedSelect: Personalized Federated Learning with Customized Selection of Parameters for...

FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning

3 Apr 2024CVPR 2024 1arXiv:2404.02478archive 2025-07-28

Rishub Tamirisa, Chulin Xie, Wenxuan Bao, Andy Zhou, Ron Arel, Aviv Shamsian

Standard federated learning approaches suffer when client data distributions have sufficient heterogeneity. Recent methods addressed the client data heterogeneity issue via personalized federated learning (PFL) - a class of FL algorithms aiming to personalize learned global knowledge to better suit the clients' local data distributions. Existing PFL methods usually decouple global updates in deep neural networks by performing personalization on particular layers (i.e. classifier heads) and global aggregation for the rest of the network. However, preselecting network layers for personalization may result in suboptimal storage of global knowledge. In this work, we propose FedSelect, a novel PFL algorithm inspired by the iterative subnetwork discovery procedure used for the Lottery Ticket Hypothesis. FedSelect incrementally expands subnetworks to personalize client parameters, concurrently conducting global aggregations on the remaining parameters. This approach enables the personalization of both client parameters and subnetwork structure during the training process. Finally, we show that FedSelect outperforms recent state-of-the-art PFL algorithms under challenging client data heterogeneity settings and demonstrates robustness to various real-world distributional shifts. Our code is available at https://github.com/lapisrocks/fedselect.

PaperPDFConference PDFCodeCode 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 19 code samples harvested from 1 repository linked to this paper: 16 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 9 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: 19 samples from 1 repository, 16 ran (6 with no instrument failure; 10 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.

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

lapisrocks/fedselect officialmentioned in papermentioned on GitHubpytorchSyntology: 19 samples, 16 ran (10 instrument-failed) · 3 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

19 samples harvested: 16 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 3 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.

3ran · honoured contract
9ran · our draft was wrong
1ran; the contract check could not run
3ran
3unverified

Licence: 0 of the 19 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 lapisrocks/fedselect. “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.

lapisrocks/fedselect official repository 19 samples, 16 ran (10 instrument-failed) · 3 unverified
DatasetSplit in 7 papers fedselect.py ran MIT (permissive) · b2313014ce8d5048 · report fixture: returned DatasetSplit · level recorded 2026-09-22
MaskLocalAltSGD fedselect.py ran MIT (permissive) · 05acbeca87ff497d · report fixture: returned MaskLocalAltSGD · level recorded 2026-09-22
_violates_bound fedselect.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · d9a08753f47b4b11 · report fixture: signature mask:Tensor/2/float, bound:float/0/float, invert:bool/0/bool · returned bool · level recorded 2026-09-22
add_masks fedselect.py ran · our draft was wrong MIT (permissive) · f2d184a11a427da7 · report fixture: signature server_dict:dict/0/?, client_dict:dict/0/?, invert:bool/0/bool · returned OrderedDict · level recorded 2026-09-22
add_server_weights fedselect.py ran · our draft was wrong MIT (permissive) · e6e3c2c4cd5c033c · report fixture: signature server_weights:dict/0/?, client_weights:dict/0/?, client_mask:dict/0/?, invert:bool/0/bool · returned OrderedDict · level recorded 2026-09-22
broadcast_server_to_client_initialization fedselect.py ran · our draft was wrong MIT (permissive) · 09941af00dbe7aa1 · report fixture: signature server_weights:dict/0/?, mask:dict/0/?, client_initialization:dict/0/? · returned OrderedDict · level recorded 2026-09-22
cross_client_eval fedselect.py ran · honoured contract MIT (permissive) · 948f6eaf9dbe70c8 · report fixture: signature model:callable/0/?, client_state_dicts:dict/0/?, dataset_train:SimpleDataset/0/?, dataset_test:SimpleDataset/0/?, dict_users_train:dict/0/?, dict_users_test:dict/0/?, args:Args/0/?, no_cross:bool/0/bool · returned Tensor · level recorded 2026-09-22
delta_update fedselect.py ran · our draft was wrong MIT (permissive) · 56d8d20eb64efc68 · report fixture: signature prune_percent:float/0/float, current_state_dict:dict/0/?, prev_state_dict:dict/0/?, current_mask:dict/0/?, bound:float/0/float, invert:bool/0/bool · returned OrderedDict · level recorded 2026-09-22
div_server_weights fedselect.py ran · our draft was wrong MIT (permissive) · 06848736b32a3ad6 · report fixture: signature server_weights:dict/0/?, server_mask:dict/0/? · returned OrderedDict · level recorded 2026-09-22
eval_layer_sparsity fedselect.py ran · our draft was wrong MIT (permissive) · 111f70a6f268709f · report fixture: signature mask:dict/0/?, layer_name:str/0/str · returned tuple · level recorded 2026-09-22
evaluate in 514 papers fedselect.py ran · honoured contract MIT (permissive) · 9af578129e5fbde5 · report fixture: signature model:callable/0/?, ldr_test:DataLoader/0/?, args:Args/0/? · returned float · level recorded 2026-09-22
get_mask_from_delta fedselect.py ran · our draft was wrong MIT (permissive) · 71427e03a95c01eb · report fixture: signature prune_percent:float/0/float, current_state_dict:dict/0/?, prev_state_dict:dict/0/?, current_mask:dict/0/?, bound:float/0/float, invert:bool/0/bool · returned OrderedDict · level recorded 2026-09-22
init_mask_zeros fedselect.py ran · our draft was wrong MIT (permissive) · 23ec196a055705f6 · report fixture: signature model:callable/0/? · returned OrderedDict · level recorded 2026-09-22
prepare_dataloaders fedselect.py ran MIT (permissive) · 997128aa3682c39c · report fixture: signature dataset_train:SimpleDataset/0/?, dict_users_train:list/1/int, dataset_test:SimpleDataset/0/?, dict_users_test:list/1/int, args:Args/0/? · returned tuple · level recorded 2026-09-22
print_nonzeros fedselect.py ran · honoured contract MIT (permissive) · 396c8158b6badd56 · report fixture: signature model:dict/0/?, verbose:bool/0/bool, invert:bool/0/bool · returned float64 · level recorded 2026-09-22
train_personalized fedselect.py ran · our draft was wrong MIT (permissive) · 3341e398e8f8ec8a · report fixture: signature model:callable/0/?, ldr_train:list/1/tuple, mask:dict/0/?, args:Args/0/?, initialization:NoneType/0/?, verbose:bool/0/bool, eval:bool/0/bool · returned tuple · level recorded 2026-09-22
fedselect_algorithm fedselect.py unverified MIT (permissive) · 13b39ed7d451ca4d · report
local_alt fedselect.py unverified MIT (permissive) · 7c4602b460e62e29 · report
print_lth_stats fedselect.py unverified MIT (permissive) · 22016817f52e1a70 · 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for FedSelect (graph method: FedSelect). 19 bricks; individually on a fixture: 16 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 3 honoured, 0 violated, 3 with no contract checked; 10 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. fedselect_algorithm entry · level 0 · unverified · 13b39ed7d451ca4d
  2. add_masks helper · level 1 · ran · our draft was wrong · f2d184a11a427da7
  3. add_server_weights helper · level 1 · ran · our draft was wrong · e6e3c2c4cd5c033c
  4. broadcast_server_to_client_initialization helper · level 1 · ran · our draft was wrong · 09941af00dbe7aa1
  5. cross_client_eval helper · level 1 · ran · honoured contract · 948f6eaf9dbe70c8
  6. delta_update helper · level 1 · ran · our draft was wrong · 56d8d20eb64efc68
  7. div_server_weights helper · level 1 · ran · our draft was wrong · 06848736b32a3ad6
  8. init_mask_zeros helper · level 1 · ran · our draft was wrong · 23ec196a055705f6
  9. prepare_dataloaders sampler · level 1 · ran · 997128aa3682c39c
  10. train_personalized update_rule · level 1 · ran · our draft was wrong · 3341e398e8f8ec8a
  11. evaluate metric · level 1 · ran · honoured contract · 9af578129e5fbde5
  12. get_mask_from_delta helper · level 1 · ran · our draft was wrong · 71427e03a95c01eb
  13. print_lth_stats helper · level 0 · unverified · 22016817f52e1a70
  14. DatasetSplit helper · level 1 · ran · b2313014ce8d5048
  15. MaskLocalAltSGD helper · level 1 · ran · 05acbeca87ff497d
  16. local_alt helper · level 0 · unverified · 7c4602b460e62e29
  17. _violates_bound helper · level 1 · ran; the contract check could not run (RAISES) · d9a08753f47b4b11
  18. eval_layer_sparsity helper · level 1 · ran · our draft was wrong · 111f70a6f268709f
  19. print_nonzeros helper · level 1 · ran · honoured contract · 396c8158b6badd56

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="2404.02478") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Federated 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