Papers › Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via...

Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium

21 Oct 2024arXiv:2410.16432archive 2025-07-28

Mehdi Yazdani-Jahromi, Ali Khodabandeh Yalabadi, Amirarsalan Rajabi, Aida Tayebi, Ivan Garibay, Ozlem Ozmen Garibay

The persistent challenge of bias in machine learning models necessitates robust solutions to ensure parity and equal treatment across diverse groups, particularly in classification tasks. Current methods for mitigating bias often result in information loss and an inadequate balance between accuracy and fairness. To address this, we propose a novel methodology grounded in bilevel optimization principles. Our deep learning-based approach concurrently optimizes for both accuracy and fairness objectives, and under certain assumptions, achieving proven Pareto optimal solutions while mitigating bias in the trained model. Theoretical analysis indicates that the upper bound on the loss incurred by this method is less than or equal to the loss of the Lagrangian approach, which involves adding a regularization term to the loss function. We demonstrate the efficacy of our model primarily on tabular datasets such as UCI Adult and Heritage Health. When benchmarked against state-of-the-art fairness methods, our model exhibits superior performance, advancing fairness-aware machine learning solutions and bridging the accuracy-fairness gap. The implementation of FairBiNN is available on https://github.com/yazdanimehdi/FairBiNN.

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.

Syntology holds a reference implementation of Fair Bilevel Neural Network (FairBiNN), generated from the paper text (not the authors' code), at level 2 on Syntology's ladder: V2 “two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs” “neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Fair Bilevel Neural Network (FairBiNN)') (how to connect); the free check have('2410.16432') needs no token.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 20 code samples harvested from 2 repositories linked to this paper: 16 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 0 violated, 8 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 4 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: 17 samples from 1 repository, 13 ran (9 with no instrument failure; 4 where Syntology's instrument failed); community (archive-listed): 3 samples from 1 repository, 3 ran (2 with no instrument failure; 1 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 16 samples that ran have no recorded date.

yazdanimehdi/fairbinn officialmentioned in papermentioned on GitHubpytorchMITSyntology: 17 samples, 13 ran (4 instrument-failed) · 4 unverified report
yazdanimehdi/Distraction_Fairness mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (1 instrument-failed) · 0 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

20 samples harvested: 16 ran (of which 3 constructed an object rather than computing a result; 11 with no instrument failure: 3 honoured, 0 violated, 8 with no contract checked; 5 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.

3ran · honoured contract
4ran · our draft was wrong
1ran; the contract check could not run
8ran
4unverified

Licence: 4 of the 20 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 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.

yazdanimehdi/fairbinn official repository 17 samples, 13 ran (4 instrument-failed) · 4 unverified
get_pareto_front train_tabular.py ran · our draft was wrong MIT (permissive) · c499ae6c68741884 · report fixture: signature arr:list/1/list, x_dominates_y:callable/0/? · returned list · level recorded, date not recorded
AttributeClassifierAblation models/tabular.py ran · metamorphic tier: deterministic MIT (permissive) · 1efa65eedfc30d0f · report fixture: returned AttributeClassifierAblation · level recorded 2026-09-22
demographic_parity_difference_soft metrics.py ran MIT (permissive) · 91a155461a8b47ea · report fixture: signature y:Tensor/1/float, c:Tensor/1/int, y_hat:Tensor/2/float · returned tuple · level recorded 2026-09-26
demographic_parity_ratio_soft metrics.py ran MIT (permissive) · 42d9f9502b5a309f · report fixture: signature y:ndarray/1/int, c:ndarray/1/int, y_hat:ndarray/2/float · returned tuple · level recorded 2026-09-26
domination train_tabular.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic MIT (permissive) · 296c6f442ab98eb3 · report fixture: signature x1:list/1/int, x2:list/1/int · returned bool · level recorded, date not recorded
education_func data_loading/load_adult.py ran · honoured contract fingerprinted MIT (permissive) · 949a08f0162e758d · report fixture: signature x:str/0/str · returned int · level recorded 2026-09-26
encode_onehot in 24 papers
census: 3 implementations from 5 papers, 2 distinct outputs across 2 buckets, one shared input per bucket
utils.py ran · our draft was wrong MIT (permissive) · 19be62d06f0eec5f · report fixture: signature labels:list/1/int · returned ndarray · level recorded 2026-09-26
fwd_pass models/vision.py ran MIT (permissive) · b5e02eb6ccb5958c · report fixture: signature x:list/1/list, sens:float/0/float, y_l:list/1/float, criterion_dp:callable/0/?, criterion_acc:callable/0/?, optimizer_dp:SGD/0/?, optimizer_acc:SGD/0/?, model:callable/0/? · returned tuple · level recorded 2026-09-26
gather_labels data_loading/load_health.py ran · our draft was wrong MIT (permissive) · 45506eb048d6e3a1 · report fixture: signature df:ndarray/2/object · returned list · level recorded 2026-09-26
load_data in 700 papers utils.py ran MIT (permissive) · ba042693993b4109 · report fixture: signature path:str/0/str, dataset:str/0/str · returned tuple · level recorded 2026-09-26
load_pokec utils.py ran MIT (permissive) · 5ec0c9199119dc47 · report fixture: signature dataset:str/0/str, sens_attr:str/0/str, predict_attr:str/0/str, path:str/0/str, label_number:int/0/int, sens_number:int/0/int, seed:int/0/int, test_idx:bool/0/bool · returned tuple · level recorded 2026-09-26
marital_func data_loading/load_adult.py ran · honoured contract fingerprinted MIT (permissive) · 75fabfad2b5e38a5 · report fixture: signature x:str/0/str · returned int · level recorded 2026-09-26
work_func data_loading/load_adult.py ran · honoured contract fingerprinted MIT (permissive) · aaed6266b7af872f · report fixture: signature x:str/0/str · returned int · level recorded 2026-09-26
dataset_construction models/vision.py unverified MIT (permissive) · 8247882e107084b3 · report
fair_metric train_graph.py unverified MIT (permissive) here; the stored copy is pointer only · 2177e2a3db468eee · report
fwd_pass train_tabular.py unverified MIT (permissive) · b15f7a302a6462cc · report
test_func models/vision.py unverified MIT (permissive) · b3e810bc6ecacc34 · report
yazdanimehdi/Distraction_Fairness community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
AttributeClassifier model.py ran no licence file found · pointer only · 1c46dba6b6061aaa · report fixture: returned AttributeClassifier · level recorded 2026-09-22
MultiHeadAttention in 124 papers
census: 9 implementations from 7 papers, 9 distinct outputs across 3 buckets, one shared input per bucket
model.py ran no licence file found · pointer only · 687fd6594c87ed5b · report fixture: returned MultiHeadAttention · level recorded 2026-09-22
scaled_dot_product in 9 papers model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 3590e425c7c27d55 · report fixture: signature q:Tensor/3/float, k:Tensor/3/float, v:Tensor/3/float, mask:Tensor/3/float · returned tuple · level recorded 2026-09-22

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. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. 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. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". 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. Where an assembly's phrase has no constructed figure, a brick that ran is not among the harvested samples this build reads, and whether a brick's run only constructed an object is read from that brick's harvested sample, so the figure was not counted; it does not say there were none.

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

generated Assembly for Fair Bilevel Neural Network (FairBiNN) (graph method: Fair Bilevel Neural Network (FairBiNN)), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 2).

label matches by construction: the code was generated for this method (not judged by a model)

  1. compute_accuracy_loss entry · level 2 · ran · faf1d113bad9e49f16fd8770a62feb773ca1b596bbfc47e49ef0f951ed188b9b

2 sibling assemblies for Fair Bilevel Neural Network (FairBiNN) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Fair Bilevel Neural Network (FairBiNN) (graph method: Fair Bilevel Neural Network (FairBiNN)). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified; the one sample that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 2 siblings

  1. AttributeClassifierAblation entry · level 1 · ran · 1efa65eedfc30d0f

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

one of 2 siblings

  1. AttributeClassifier entry · level 1 · ran · 1c46dba6b6061aaa
  2. MultiHeadAttention model · level 1 · ran · 687fd6594c87ed5b
  3. scaled_dot_product helper · level 1 · ran · our draft was wrong · 3590e425c7c27d55

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="2410.16432") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Bilevel OptimizationFairness

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