Papers › On Memorization in Diffusion Models

On Memorization in Diffusion Models

4 Oct 2023arXiv:2310.02664archive 2025-07-28

Xiangming Gu, Chao Du, Tianyu Pang, Chongxuan Li, Min Lin, Ye Wang

Due to their capacity to generate novel and high-quality samples, diffusion models have attracted significant research interest in recent years. Notably, the typical training objective of diffusion models, i.e., denoising score matching, has a closed-form optimal solution that can only generate training data replicating samples. This indicates that a memorization behavior is theoretically expected, which contradicts the common generalization ability of state-of-the-art diffusion models, and thus calls for a deeper understanding. Looking into this, we first observe that memorization behaviors tend to occur on smaller-sized datasets, which motivates our definition of effective model memorization (EMM), a metric measuring the maximum size of training data at which a learned diffusion model approximates its theoretical optimum. Then, we quantify the impact of the influential factors on these memorization behaviors in terms of EMM, focusing primarily on data distribution, model configuration, and training procedure. Besides comprehensive empirical results identifying the influential factors, we surprisingly find that conditioning training data on uninformative random labels can significantly trigger the memorization in diffusion models. Our study holds practical significance for diffusion model users and offers clues to theoretical research in deep generative models. Code is available at https://github.com/sail-sg/DiffMemorize.

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 14 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 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: 14 samples from 1 repository, 10 ran (5 with no instrument failure; 5 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 1 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. 5 of the 10 samples that ran have no recorded date.

sail-sg/DiffMemorize officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 10 ran (5 instrument-failed) · 4 unverified report
sixuli/ddpm_and_kde mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to A Good Score Does not Lead to A Good Generative Model (arXiv:2401.04856; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 3 honoured, 0 violated, 1 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. 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

14 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 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
2ran
4unverified

Licence: 5 of the 14 samples are pointer only, meaning Syntology does not serve that copy's text. For 5 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 sail-sg/DiffMemorize. “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.

sail-sg/DiffMemorize official repository 14 samples, 10 ran (5 instrument-failed) · 4 unverified
file_ext in 37 papers dataset_utils/dataset_diversity.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · a2b45afa097b55b6 · report fixture: signature name:str/0/str · returned str · level recorded, date not recorded
file_ext in 37 papers mem_ratio.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · b1986232479684ae · report fixture: signature fname:str/0/str · returned str · level recorded 2026-09-25
find_class_folders dataset_utils/sample_imagenet.py ran MIT (permissive) · 2bc3b7a1e6f0984b · report fixture: signature class_name:str/0/str · returned list · level recorded 2026-09-24
format_time in 140 papers dnnlib/util.py ran · our draft was wrong fingerprinted MIT (permissive) · 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 MIT (permissive) · 32af001972a0699f · report fixture: signature seconds:float/0/float · returned str · level recorded, date not recorded
maybe_min in 36 papers dataset_utils/dataset_diversity.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · dd1dc700e87f36cc · report fixture: signature a:int/0/int, b:NoneType/0/? · returned int · level recorded, date not recorded
parse_int_list in 59 papers generate_edm.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · cacd4f6ec202d9b4 · report fixture: signature s:str/0/str · returned list · level recorded, date not recorded
parse_tuple in 34 papers dataset_utils/dataset_diversity.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 07b21b35ecb4815c · report fixture: signature s:str/0/str · returned tuple · level recorded 2026-09-24
sample_images dataset_utils/sample_imagenet.py ran MIT (permissive) · f1eb8f458487f3ab · report fixture: signature root:str/0/str, class_folders:list/1/str, num_samples:int/0/int, save_path:str/0/str · returned list · level recorded 2026-09-24
weight_init in 73 papers training/networks.py ran; the contract check could not run (RAISES) MIT (permissive) · 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_edm.py unverified MIT (permissive) · 9fbf646e18eed1db · report
ask_yes_no in 70 papers dnnlib/util.py unverified MIT (permissive) · 9d31d2c4cd16bb2d · report
edm_sampler in 34 papers generate_edm.py unverified MIT (permissive) · 8b16b0674af254db · report
load_cifar10_zip mem_ratio.py unverified MIT (permissive) · ad63e5e1c1e32ab7 · report

Tasks

DenoisingMemorization

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