Papers › Learning Debiased Classifier with Biased Committee

Learning Debiased Classifier with Biased Committee

22 Jun 2022arXiv:2206.10843archive 2025-07-28

Nayeong Kim, Sehyun Hwang, Sungsoo Ahn, Jaesik Park, Suha Kwak

Neural networks are prone to be biased towards spurious correlations between classes and latent attributes exhibited in a major portion of training data, which ruins their generalization capability. We propose a new method for training debiased classifiers with no spurious attribute label. The key idea is to employ a committee of classifiers as an auxiliary module that identifies bias-conflicting data, i.e., data without spurious correlation, and assigns large weights to them when training the main classifier. The committee is learned as a bootstrapped ensemble so that a majority of its classifiers are biased as well as being diverse, and intentionally fail to predict classes of bias-conflicting data accordingly. The consensus within the committee on prediction difficulty thus provides a reliable cue for identifying and weighting bias-conflicting data. Moreover, the committee is also trained with knowledge transferred from the main classifier so that it gradually becomes debiased along with the main classifier and emphasizes more difficult data as training progresses. On five real-world datasets, our method outperforms prior arts using no spurious attribute label like ours and even surpasses those relying on bias labels occasionally.

PaperPDFCodeCode 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 10 code samples harvested from 2 repositories linked to this paper: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 8 ran (7 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 1 sample 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nayeong-v-kim/lwbc officialmentioned in paperpytorchMITSyntology: 9 samples, 8 ran (1 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

10 samples harvested: 9 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 1 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

2ran · honoured contract
1ran · violated contract
1ran · our draft was wrong
5ran
1unverified

Licence: 3 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 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.

nayeong-v-kim/lwbc official repository 9 samples, 8 ran (1 instrument-failed) · 1 unverified
ce in 7 papers LWBC/utils.py ran MIT (permissive) · baf0825d62f43593 · report fixture: signature outputs:Tensor/2/float, labels:Tensor/1/int, reduce:bool/0/bool · returned Tensor · level recorded 2026-09-25
cosine_rampdown in 15 papers SSL/main_byol.py ran fingerprinted MIT (permissive) · a1358ef8d9401bec · report fixture: signature current:int/0/int, rampdown_length:int/0/int · returned float · level recorded 2026-09-25
default in 430 papers SSL/byol/builder.py ran · violated contract MIT (permissive) · 1c0f269ae9673b08 · report fixture: signature val:NoneType/0/?, def_val:int/0/int · returned int · level recorded 2026-09-22
flatten in 178 papers
census: 4 implementations from 7 papers, 4 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 3, kind float, dtype float32
SSL/byol/builder.py ran · honoured contract fingerprinted MIT (permissive) · 4daa3e876f494d75 · report fixture: signature t:Tensor/3/float · returned Tensor · level recorded 2026-09-22
get_classifier in 16 papers LWBC/utils.py ran MIT (permissive) · ddba6a6202534e39 · report fixture: signature num_linear:str/0/str, f_dim:int/0/int, output_dim:int/0/int, linear_bias:bool/0/bool · returned Sequential · level recorded 2026-09-25
linear_rampup in 33 papers SSL/main_byol.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 069122bd5268cc56 · report fixture: signature current:int/0/int, rampup_length:int/0/int · returned float · level recorded 2026-09-25
num_correct_all LWBC/utils.py ran MIT (permissive) · b93663f30ffebf65 · report fixture: signature outputs:Tensor/2/float, labels:Tensor/1/int, sensitive:Tensor/1/int, num_class:int/0/int, flag:int/0/int · returned tuple · level recorded 2026-09-25
singleton in 23 papers SSL/byol/builder.py ran · our draft was wrong MIT (permissive) · c6bc247ffa36099c · report fixture: signature cache_key:str/0/str · returned function · level recorded 2026-09-22
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
SSL/main_byol.py unverified MIT (permissive) here; the stored copy is pointer only · 9b8289076669fe4f · report
alinlab/LfF found in paper text by Syntology 1 sample, 1 ran (0 instrument-failed) · 0 unverified
GeneralizedCELoss module/loss.py ran no licence file found · pointer only · 8a53821f55fe659d · report fixture: signature logits:Tensor/2/float, targets:Tensor/1/int · returned Tensor · level recorded 2026-09-24

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 Learning Debiased Classifier with Biased Committee (graph method: Learning Debiased Classifier with Biased Committee). 1 brick; individually on a fixture: 1 ran (of which 0 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) · 0 unverified. The assembly has not been run end-to-end.

  1. GeneralizedCELoss entry · level 1 · ran · 8a53821f55fe659d

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="2206.10843") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Attribute

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