SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2407.15328 · 2024

Iterative Ensemble Training with Anti-Gradient Control for Mitigating Memorization in Diffusion Models

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 7 failures of our instrument; 1 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2407.15328.json · badge: /api/ran/2407.15328.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
liuxiao-guan/iet_agc canonical (classifier label)
classifier basis: census
7 ran · 1 no recorded run
FunctionStatusWhere it lives
calculate_frechet_distance Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liuxiao-guan/iet_agc/score/fid.py
pointer only (licence: WTFPL) · get_code("cd3edab30cfead44")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

custom_sort_key Ran
ran; our contract draft was wrong, not the code
liuxiao-guan/iet_agc/attack/all_in.py
pointer only (licence: WTFPL) · get_code("68b817601e8d8589")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract Ran
ran; our contract draft was wrong, not the code
liuxiao-guan/iet_agc/diffusion.py
pointer only (licence: WTFPL) · get_code("6a78f18d5b2ce056")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_inception_score Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liuxiao-guan/iet_agc/score/inception_score.py
pointer only (licence: WTFPL) · get_code("9b81ae7906ed29eb")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

maintain_array Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
liuxiao-guan/iet_agc/attack/all_in.py
pointer only (licence: WTFPL) · get_code("3cd1ed6d022ffb34")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

sqrt_newton_schulz Ran
ran; our contract draft was wrong, not the code
liuxiao-guan/iet_agc/score/fid.py
pointer only (licence: WTFPL) · get_code("2dfa8886e774088c")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

torch_cov Ran
ran; our contract draft was wrong, not the code
liuxiao-guan/iet_agc/score/fid.py
pointer only (licence: WTFPL) · get_code("b304af5c4fc5341a")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

get_inception_and_fid_score Not yet run
unverified (harvested, no recorded run)
liuxiao-guan/iet_agc/score/both.py
pointer only (licence: WTFPL) · get_code("526c471ba9b04752")
How it ran

The body of this sample is withheld: WTFPL, as GitHub detects it on this paper's repository, liuxiao-guan/iet_agc, is not in the permissive set Syntology serves inline. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 6 are also present in other papers whose code we hold (6 with at least one paper dated earlier, 0 the same month, 3 later) and 2 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
extract 12 other papers
9 dated earlier, 3 later · 3 only as an assembly brick
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2302.01316 (2023-02)
Are Diffusion Models Vulnerable to Membership Inference Attacks?
2305.00562 (2023-05)
Class-Balancing Diffusion Models
and 9 more not named here
torch_cov 12 other papers
11 dated earlier, 1 later
1406.2661 (2014-06)
Generative Adversarial Networks
1811.10597 (2018-11)
GAN Dissection: Visualizing and Understanding Generative Adversarial Networks
1912.05270 (2019-12)
MineGAN: effective knowledge transfer from GANs to target domains with few images
and 9 more not named here
sqrt_newton_schulz 5 other papers
4 dated earlier, 1 later
2305.19638 (2023-05)
A Unified Framework for U-Net Design and Analysis
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2310.11440 (2023-10)
EvalCrafter: Benchmarking and Evaluating Large Video Generation Models
and 2 more not named here
calculate_frechet_distance 3 other papers
3 dated earlier
2305.19638 (2023-05)
A Unified Framework for U-Net Design and Analysis
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models
get_inception_and_fid_score 3 other papers
3 dated earlier
2305.19638 (2023-05)
A Unified Framework for U-Net Design and Analysis
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models
get_inception_score 3 other papers
3 dated earlier
2305.19638 (2023-05)
A Unified Framework for U-Net Design and Analysis
2310.03337 (2023-10)
Denoising Diffusion Step-aware Models
2405.05846 (2024-05)
An Inversion-based Measure of Memorization for Diffusion Models

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Diffusion models, known for their tremendous ability to generate novel and high-quality samples, have recently raised concerns due to their data memorization behavior, which poses privacy risks. Recent approaches for memory mitigation either only focused on the text modality problem in cross-modal generation tasks or utilized data augmentation strategies. In this paper, we propose a novel training framework for diffusion models from the perspective of visual modality, which is more generic and fundamental for mitigating memorization. To facilitate forgetting of stored information in diffusion model parameters, we propose an iterative ensemble training strategy by splitting the data into multiple shards for training multiple models and intermittently aggregating these model parameters. Moreover, practical analysis of losses illustrates that the training loss for easily memorable images tends to be obviously lower. Thus, we propose an anti-gradient control method to exclude the sample with a lower loss value from the current mini-batch to avoid memorizing. Extensive experiments and analysis on four datasets are conducted to illustrate the effectiveness of our method, and results show that our method successfully reduces memory capacity while even improving the performance slightly. Moreover, to save the computing cost, we successfully apply our method to fine-tune the well-trained diffusion models by limited epochs, demonstrating the applicability of our method. Code is available in https://github.com/liuxiao-guan/IET_AGC.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2407.15328")
get_code_for_paper("2407.15328")
have("2407.15328")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2407.15328.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2407.15328.svg)](https://syntology.ai/paper/2407.15328)

Connect an agent — have() is free.