Papers › Eliminating Domain Bias for Federated Learning in Representation Space

Eliminating Domain Bias for Federated Learning in Representation Space

25 Nov 2023NeurIPS 2023 11arXiv:2311.14975archive 2025-07-28

Jianqing Zhang, Yang Hua, Jian Cao, Hao Wang, Tao Song, Zhengui Xue, Ruhui Ma, Haibing Guan

Recently, federated learning (FL) is popular for its privacy-preserving and collaborative learning abilities. However, under statistically heterogeneous scenarios, we observe that biased data domains on clients cause a representation bias phenomenon and further degenerate generic representations during local training, i.e., the representation degeneration phenomenon. To address these issues, we propose a general framework Domain Bias Eliminator (DBE) for FL. Our theoretical analysis reveals that DBE can promote bi-directional knowledge transfer between server and client, as it reduces the domain discrepancy between server and client in representation space. Besides, extensive experiments on four datasets show that DBE can greatly improve existing FL methods in both generalization and personalization abilities. The DBE-equipped FL method can outperform ten state-of-the-art personalized FL methods by a large margin. Our code is public at https://github.com/TsingZ0/DBE.

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 16 code samples harvested from 2 repositories linked to this paper: 12 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 6 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 14 samples from 1 repository, 11 ran (5 with no instrument failure; 6 where Syntology's instrument failed); community (archive-listed): 2 samples from 1 repository, 1 ran (1 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.

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. 2 of the 12 samples that ran have no recorded date.

tsingz0/dbe officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: 14 samples, 11 ran (6 instrument-failed) · 3 unverified report
TsingZ0/PFLlib pytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 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

16 samples harvested: 12 ran (of which 2 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
6ran · our draft was wrong
5ran
4unverified

Licence: 3 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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. “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.

tsingz0/dbe official repository 14 samples, 11 ran (6 instrument-failed) · 3 unverified
Client in 24 papers system/flcore/clients/clientDBE.py ran Apache-2.0 (permissive) · bcb93a525852f945 · report fixture: returned Client · level recorded 2026-09-22
DLG in 5 papers system/utils/dlg.py ran Apache-2.0 (permissive) · b215fd88c9a94b27 · report fixture: signature net:callable/0/?, origin_grad:list/1/Tensor, target_inputs:list/1/tuple · returned float · level recorded 2026-09-24
alexnet in 42 papers system/flcore/trainmodel/alexnet.py ran · our draft was wrong Apache-2.0 (permissive) · 4839e6f3a569f1b9 · report fixture: signature pretrained:bool/0/bool, progress:bool/0/bool · returned AlexNet · level recorded 2026-09-24
conv1x1 in 691 papers system/flcore/trainmodel/resnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 2a80220dabcb742a · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
conv3x3 in 1,376 papers system/flcore/trainmodel/resnet.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 600ff2c45e0de056 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int, groups:int/0/int, dilation:int/0/int · returned Conv2d · level recorded, date not recorded
mobilenet_v2 in 23 papers system/flcore/trainmodel/mobilenet_v2.py ran Apache-2.0 (permissive) · 22b172e83bc1a35c · report fixture: signature num_classes:int/0/int, width_mult:float/0/float, inverted_residual_setting:NoneType/0/?, round_nearest:int/0/int, block:NoneType/0/?, norm_layer:NoneType/0/? · returned MobileNetV2 · level recorded 2026-09-24
psnr in 88 papers
census: 9 implementations from 11 papers, 6 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 4 of 4, arg 1: rank 3, kind float, dtype float32 · arg 2: rank 3, kind float, dtype float32
system/utils/dlg.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 4946a7bb15ea5717 · report fixture: signature original:ndarray/3/float, contrast:ndarray/3/float · returned float · level recorded 2026-09-22
read_client_data in 11 papers system/flcore/clients/clientDBE.py ran · our draft was wrong Apache-2.0 (permissive) · 595b80d1ed9df88b · report fixture: signature dataset:str/0/str, idx:int/0/int, is_train:bool/0/bool · returned list · level recorded 2026-09-22
read_client_data in 11 papers system/utils/data_utils.py ran Apache-2.0 (permissive) · 10541ee086fd6a62 · report fixture: signature dataset:str/0/str, idx:int/0/int, is_train:bool/0/bool · returned list · level recorded 2026-09-24
read_client_data_Shakespeare system/flcore/clients/clientDBE.py ran · our draft was wrong Apache-2.0 (permissive) · 63f5fae02e590aa7 · report fixture: signature dataset:str/0/str, idx:int/0/int, is_train:bool/0/bool · returned list · level recorded 2026-09-22
read_client_data_text in 7 papers system/flcore/clients/clientDBE.py ran · our draft was wrong Apache-2.0 (permissive) · 62bd3835aba88265 · report fixture: signature dataset:str/0/str, idx:int/0/int, is_train:bool/0/bool · returned list · level recorded 2026-09-22
clientDBE system/flcore/clients/clientDBE.py unverified Apache-2.0 (permissive) · cbbf4025770d2739 · report
read_client_data_text in 7 papers system/utils/data_utils.py unverified Apache-2.0 (permissive) · 736b76e55626f3c9 · report
read_data in 132 papers system/utils/data_utils.py unverified Apache-2.0 (permissive) · 2e468f03b54c3418 · report
TsingZ0/PFLlib community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
Client in 24 papers system/flcore/clients/clientdbe.py ran Apache-2.0 (permissive) · b34107b395a46a1f · report fixture: returned Client · level recorded 2026-09-22
clientDBE system/flcore/clients/clientdbe.py unverified Apache-2.0 (permissive) · 65f41de191a63731 · 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.

2 assemblies on this paper: 2 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Domain Bias Eliminator (DBE) (graph method: Domain Bias Eliminator (DBE)). 6 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. clientDBE entry · level 0 · unverified · cbbf4025770d2739
  2. Client helper · level 1 · ran · bcb93a525852f945
  3. read_client_data helper · level 1 · ran · our draft was wrong · 595b80d1ed9df88b
  4. read_client_data_Shakespeare helper · level 1 · ran · our draft was wrong · 63f5fae02e590aa7
  5. read_client_data_text helper · level 1 · ran · our draft was wrong · 62bd3835aba88265
  6. read_data helper · level 0 · unverified · 2e468f03b54c3418

harvested Assembly for Domain Bias Eliminator (DBE) (graph method: Domain Bias Eliminator (DBE)). 7 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. clientDBE entry · level 0 · unverified · 65f41de191a63731
  2. Client helper · level 1 · ran · b34107b395a46a1f
  3. read_client_data helper · level 0 · unverified · ee5f6af39c3092db
  4. process_Shakespeare helper · level 1 · ran · our draft was wrong · 13727b959b74cb36
  5. process_image helper · level 1 · ran · our draft was wrong · eeaf321abdedfa1f
  6. process_text helper · level 1 · ran · our draft was wrong · bff598ba2b65008a
  7. read_data helper · level 1 · ran · honoured contract · 8eebe137489ff326

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="2311.14975") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Federated LearningPrivacy PreservingTransfer 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