Papers › Training Unbiased Diffusion Models From Biased Dataset

Training Unbiased Diffusion Models From Biased Dataset

2 Mar 2024arXiv:2403.01189archive 2025-07-28

Yeongmin Kim, Byeonghu Na, Minsang Park, JoonHo Jang, Dongjun Kim, Wanmo Kang, Il-Chul Moon

With significant advancements in diffusion models, addressing the potential risks of dataset bias becomes increasingly important. Since generated outputs directly suffer from dataset bias, mitigating latent bias becomes a key factor in improving sample quality and proportion. This paper proposes time-dependent importance reweighting to mitigate the bias for the diffusion models. We demonstrate that the time-dependent density ratio becomes more precise than previous approaches, thereby minimizing error propagation in generative learning. While directly applying it to score-matching is intractable, we discover that using the time-dependent density ratio both for reweighting and score correction can lead to a tractable form of the objective function to regenerate the unbiased data density. Furthermore, we theoretically establish a connection with traditional score-matching, and we demonstrate its convergence to an unbiased distribution. The experimental evidence supports the usefulness of the proposed method, which outperforms baselines including time-independent importance reweighting on CIFAR-10, CIFAR-100, FFHQ, and CelebA with various bias settings. Our code is available at https://github.com/alsdudrla10/TIW-DSM.

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 time-dependent importance reweighting, generated from the paper text (not the authors' code), at level 3 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)”; V3 “paper-derived property tests pass on both of those same two generations.” (quoted from Syntology's server card). No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='time-dependent importance reweighting') (how to connect); the free check have('2403.01189') needs no token.

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

Code

Syntology 37 code samples harvested from 3 repositories linked to this paper: 30 ran (of which 1 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 2 violated, 6 with no contract checked; 16 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 14 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: 17 samples from 1 repository, 14 ran (7 with no instrument failure; 7 where Syntology's instrument failed); found in paper text by Syntology: 20 samples from 2 repositories, 16 ran (7 with no instrument failure; 9 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.

No sample is linked to this paper from 3 of its repositories that Syntology harvested for other papers:

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. 11 of the 30 samples that ran have no recorded date.

alsdudrla10/tiw-dsm officialmentioned in papermentioned on GitHubpytorchNOASSERTIONSyntology: 17 samples, 14 ran (7 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

37 samples harvested: 30 ran (of which 1 constructed an object rather than computing a result; 14 with no instrument failure: 6 honoured, 2 violated, 6 with no contract checked; 16 where Syntology's instrument failed) · 7 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.

6ran · honoured contract
2ran · violated contract
14ran · our draft was wrong
2ran; the contract check could not run
6ran
7unverified

Licence: 37 of the 37 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 3 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.

alsdudrla10/tiw-dsm official repository 17 samples, 14 ran (7 instrument-failed) · 3 unverified
approx_standard_normal_cdf in 150 papers
census: 4 implementations from 14 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
guided_diffusion/losses.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cfd76fd0d89574a4 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded, date not recorded
calculate_fid_from_inception_stats in 26 papers fid.py ran · honoured contract fingerprinted no licence file found · pointer only · 45e941764344e7f3 · report fixture: signature mu:ndarray/1/float, sigma:ndarray/2/float, mu_ref:ndarray/1/float, sigma_ref:ndarray/2/float · returned float · level recorded, date not recorded
compute_t_cos_from_t_lin guided_diffusion/unet.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 7e78740874fe261b · report fixture: signature timesteps:Tensor/1/float · returned Tensor · level recorded 2026-09-24
discretized_gaussian_log_likelihood in 124 papers
census: 6 implementations from 10 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32
guided_diffusion/losses.py ran · our draft was wrong no licence file found · pointer only · cd33283d615fb3d7 · report fixture: signature x:Tensor/2/float, means:Tensor/2/float, log_scales:Tensor/2/float · returned Tensor · level recorded, date not recorded
file_ext in 37 papers dataset_tool.py ran · our draft was wrong fingerprinted no licence file found · pointer only · a2b45afa097b55b6 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
format_time in 140 papers dnnlib/util.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 674eca7b9e1b6439 · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
format_time_brief in 69 papers dnnlib/util.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 32af001972a0699f · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
get_discriminator in 7 papers classifier_lib.py ran licence not identified · pointer only · 624251787df4cb51 · report fixture: signature latent_extractor_ckpt:callable/0/?, discriminator_ckpt:callable/0/?, enable_grad:bool/0/bool · returned function · level recorded 2026-09-24
get_reverse_discriminator classifier_lib.py ran licence not identified · pointer only · 6afce2a3a100ae5d · report fixture: signature latent_extractor_ckpt:callable/0/?, discriminator_ckpt:callable/0/?, enable_grad:bool/0/bool · returned function · level recorded 2026-09-24
maybe_min in 36 papers dataset_tool.py ran · honoured contract fingerprinted no licence file found · pointer only · dd1dc700e87f36cc · report fixture: signature a:int/0/int, b:NoneType/0/? · returned int · level recorded, date not recorded
normal_kl in 188 papers
census: 14 implementations from 24 papers, 2 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 · arg 3: rank 2, kind float, dtype float32 · arg 4: rank 2, kind float, dtype float32
guided_diffusion/losses.py ran · honoured contract fingerprinted no licence file found · pointer only · cf2798b666b231ca · report fixture: signature mean1:Tensor/2/float, logvar1:Tensor/2/float, mean2:Tensor/2/float, logvar2:Tensor/2/float · returned Tensor · level recorded 2026-09-22
parse_int_list in 59 papers generate.py ran · honoured contract no licence file found · pointer only · cacd4f6ec202d9b4 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
parse_tuple in 34 papers dataset_tool.py ran · honoured contract no licence file found · pointer only · 07b21b35ecb4815c · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-24
weight_init in 73 papers training/networks.py ran; the contract check could not run (RAISES) no licence file found · pointer only · d41a4250066bce93 · report fixture: signature shape:tuple/1/int, mode:str/0/str, fan_in:int/0/int, fan_out:int/0/int · returned Tensor · level recorded 2026-09-22
ablation_sampler in 17 papers generate.py unverified no licence file found · pointer only · 9fbf646e18eed1db · report
ask_yes_no in 70 papers dnnlib/util.py unverified no licence file found · pointer only · 9d31d2c4cd16bb2d · report
edm_sampler in 34 papers generate.py unverified no licence file found · pointer only · 8b16b0674af254db · report
alsdudrla10/DG found in paper text by Syntology 3 samples, 2 ran (1 instrument-failed) · 1 unverified
get_log_ratio classifier_lib.py ran; the contract check could not run (RAISES) licence not identified · pointer only · aa3432c25ff63849 · report fixture: signature discriminator:callable/0/?, input:Tensor/2/float, time:Tensor/1/int, class_labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
vpsde classifier_lib.py ran licence not identified · pointer only · b973e7772b10cd3a · report fixture: returned vpsde · level recorded 2026-09-22
get_grad_log_ratio classifier_lib.py unverified licence not identified · pointer only · 6e1f031f85a7338e · report
ermongroup/fairgen found in paper text by Syntology 17 samples, 14 ran (8 instrument-failed) · 3 unverified
D_arch in 21 papers src/KL-BigGAN/BigGAN.py ran · our draft was wrong no licence file found · pointer only · 85eb95cce203dfc7 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded, date not recorded
D_arch in 21 papers src/KL-BigGAN/BigGANdeep.py ran no licence file found · pointer only · a99a05ac52533be9 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded 2026-09-25
G_arch in 22 papers src/KL-BigGAN/BigGAN.py ran · our draft was wrong no licence file found · pointer only · e8c308c9283407d7 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded, date not recorded
G_arch in 22 papers src/KL-BigGAN/BigGANdeep.py ran no licence file found · pointer only · 44d6a6343f6eb182 · report fixture: signature ch:int/0/int, attention:str/0/str, ksize:str/0/str, dilation:str/0/str · returned dict · level recorded 2026-09-25
build_celeba_classification_dataset src/dataset_splits.py ran no licence file found · pointer only · c2057f330c5906c9 · report fixture: signature split:str/0/str, class_idx:int/0/int, class_idx2:NoneType/0/? · returned TensorDataset · level recorded 2026-09-24
check_integrity in 37 papers src/KL-BigGAN/dataset_utils.py ran · violated contract fingerprinted no licence file found · pointer only · 7345763c9b9300fb · report fixture: signature fpath:str/0/str, md5:str/0/str · returned bool · level recorded 2026-09-25
conv3x3 in 1,376 papers src/clf_models.py ran · our draft was wrong no licence file found · pointer only · fac5364e2f53c6db · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded, date not recorded
find_classes in 61 papers src/KL-BigGAN/datasets.py ran · our draft was wrong no licence file found · pointer only · 52d10a10fb72fb9f · report fixture: signature dir:str/0/str · returned tuple · level recorded 2026-09-24
is_image_file in 157 papers src/KL-BigGAN/datasets.py ran · violated contract no licence file found · pointer only · 4e6a8faaf8e44abe · report fixture: signature filename:str/0/str · returned bool · level recorded 2026-09-24
list_dir in 22 papers src/KL-BigGAN/dataset_utils.py ran · our draft was wrong no licence file found · pointer only · 0d8aca7e68b6e3c8 · report fixture: signature root:str/0/str, prefix:bool/0/bool · returned list · level recorded 2026-09-24
list_files in 33 papers src/KL-BigGAN/dataset_utils.py ran · our draft was wrong no licence file found · pointer only · 0fcbc473379434c0 · report fixture: signature root:str/0/str, suffix:str/0/str, prefix:bool/0/bool · returned list · level recorded 2026-09-24
load_attributes in 5 papers src/preprocess_celeba.py ran · honoured contract no licence file found · pointer only · b0b12a75d3201590 · report fixture: signature paths:list/1/str, partition:str/0/str, data_dir:str/0/str · returned Tensor · level recorded 2026-09-22
load_eval_partition src/preprocess_celeba.py ran · our draft was wrong no licence file found · pointer only · 115ca35fe166b65c · report fixture: signature partition:str/0/str, data_dir:str/0/str · returned list · level recorded 2026-09-22
make_dataset in 144 papers src/KL-BigGAN/datasets.py ran · our draft was wrong no licence file found · pointer only · 79e61b6269a450e8 · report fixture: signature dir:str/0/str, class_to_idx:dict/0/? · returned list · level recorded 2026-09-24
build_90_10_unbalanced_datasets_clf_celeba src/dataset_splits.py unverified no licence file found · pointer only · e5c036d214df6b76 · report
build_model in 469 papers src/clf_models.py unverified no licence file found · pointer only · bbf5414ac067dc67 · report
build_multi_celeba_classification_datset src/dataset_splits.py unverified no licence file found · pointer only · c6662a10d22a9f45 · 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. 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". 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.

2 assemblies on this paper: 1 harvested, 1 generated.

generated Assembly for time-dependent importance reweighting (graph method: time-dependent importance reweighting), generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 1 ran (0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer (level 3; 5 property tests passed on both).

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

  1. compute_discriminator_loss entry · level 3 · ran; the contract check could not run · 59c212a4d61f3257a3d93c4ea4a1a9129ce04b58836804fc28cd857f5f9f5a50

harvested Assembly for time-dependent importance reweighting (graph method: time-dependent importance reweighting). 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. get_grad_log_ratio entry · level 0 · unverified · 6e1f031f85a7338e
  2. get_log_ratio helper · level 1 · ran; the contract check could not run (RAISES) · aa3432c25ff63849
  3. vpsde helper · level 1 · ran · b973e7772b10cd3a

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="2403.01189") returns these assemblies with each brick's role and wiring (how to connect).

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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