Papers › Bias Propagation in Federated Learning

Bias Propagation in Federated Learning

5 Sep 2023arXiv:2309.02160archive 2025-07-28

Hongyan Chang, Reza Shokri

We show that participating in federated learning can be detrimental to group fairness. In fact, the bias of a few parties against under-represented groups (identified by sensitive attributes such as gender or race) can propagate through the network to all the parties in the network. We analyze and explain bias propagation in federated learning on naturally partitioned real-world datasets. Our analysis reveals that biased parties unintentionally yet stealthily encode their bias in a small number of model parameters, and throughout the training, they steadily increase the dependence of the global model on sensitive attributes. What is important to highlight is that the experienced bias in federated learning is higher than what parties would otherwise encounter in centralized training with a model trained on the union of all their data. This indicates that the bias is due to the algorithm. Our work calls for auditing group fairness in federated learning and designing learning algorithms that are robust to bias propagation.

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 13 code samples harvested from 1 repository linked to this paper: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 13 samples from 1 repository, 11 ran (8 with no instrument failure; 3 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

privacytrustlab/bias_in_FL officialmentioned in paperpytorchSyntology: 13 samples, 11 ran (3 instrument-failed) · 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

13 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 3 where Syntology's instrument failed) · 2 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 · our draft was wrong
2ran; the contract check could not run
8ran
2unverified

Licence: 13 of the 13 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 privacytrustlab/bias_in_FL. “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.

privacytrustlab/bias_in_FL official repository 13 samples, 11 ran (3 instrument-failed) · 2 unverified
adult_filter in 5 papers folktables/acs.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 90b47857bae57234 · report fixture: signature data:DataFrame/0/? · returned DataFrame · level recorded 2026-09-22
get_dataset in 285 papers save_information.py ran no licence file found · pointer only · 52fd482d17be998c · report fixture: signature test_dataset:MockDataset/0/? · returned tuple · level recorded 2026-09-24
get_performance save_information.py ran no licence file found · pointer only · e0a7ae34ed0264a4 · report fixture: signature model:callable/0/?, x:ndarray/2/float, y:ndarray/1/int, s:ndarray/2/int, attr_idx:int/0/int · returned tuple · level recorded 2026-09-24
get_performance_per_group utils.py ran no licence file found · pointer only · 0e88661ed82fef10 · report fixture: signature model:callable/0/?, x:ndarray/2/float, y:ndarray/1/int, s:ndarray/2/int, attr_idx:int/0/int, is_global:bool/0/bool · returned tuple · level recorded 2026-09-24
get_prediction in 12 papers save_information.py ran no licence file found · pointer only · 546b4e92c7fccfa5 · report fixture: signature model:callable/0/?, x:ndarray/2/float, y:ndarray/1/int · returned tuple · level recorded 2026-09-24
load_acs folktables/load_acs.py ran no licence file found · pointer only · ea065c05c1afcdb5 · report fixture: signature root_dir:str/0/str, states:list/1/str, year:int/0/int, horizon:str/0/str, survey:str/0/str, density:float/0/float, random_seed:int/0/int, serial_filter_list:NoneType/0/?, download:bool/0/bool · returned DataFrame · level recorded 2026-09-24
load_definitions folktables/load_acs.py ran no licence file found · pointer only · 17a0dcf9714aea52 · report fixture: signature root_dir:str/0/str, year:int/0/int, horizon:str/0/str, download:bool/0/bool · returned DataFrame · level recorded 2026-09-24
partition_dataset data_loader.py ran no licence file found · pointer only · 5b691457c7b1e8f2 · report fixture: signature y:ndarray/1/int, args:Args/0/? · returned tuple · level recorded 2026-09-24
public_coverage_filter in 5 papers folktables/acs.py ran · our draft was wrong no licence file found · pointer only · 42c7efd00fb29885 · report fixture: signature data:DataFrame/0/? · returned DataFrame · level recorded 2026-09-22
rgb utils.py ran fingerprinted no licence file found · pointer only · 144a5912b7e6b4ca · report fixture: signature x:int/0/int, y:int/0/int, z:int/0/int · returned tuple · level recorded 2026-09-24
travel_time_filter folktables/acs.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed no licence file found · pointer only · 03a154d3e52a41d9 · report fixture: signature data:DataFrame/0/? · returned DataFrame · level recorded 2026-09-22
initialize_and_download folktables/load_acs.py unverified no licence file found · pointer only · 8797cd7c6bf1010f · report
load_arguments in 5 papers fedml/arguments.py unverified no licence file found · pointer only · 31a606e515af565e · report

Tasks

FairnessFederated 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