Papers › FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score...

FP-Diffusion: Improving Score-based Diffusion Models by Enforcing the Underlying Score Fokker-Planck Equation

9 Oct 2022arXiv:2210.04296archive 2025-07-28

Chieh-Hsin Lai, Yuhta Takida, Naoki Murata, Toshimitsu Uesaka, Yuki Mitsufuji, Stefano Ermon

Score-based generative models (SGMs) learn a family of noise-conditional score functions corresponding to the data density perturbed with increasingly large amounts of noise. These perturbed data densities are linked together by the Fokker-Planck equation (FPE), a partial differential equation (PDE) governing the spatial-temporal evolution of a density undergoing a diffusion process. In this work, we derive a corresponding equation called the score FPE that characterizes the noise-conditional scores of the perturbed data densities (i.e., their gradients). Surprisingly, despite the impressive empirical performance, we observe that scores learned through denoising score matching (DSM) fail to fulfill the underlying score FPE, which is an inherent self-consistency property of the ground truth score. We prove that satisfying the score FPE is desirable as it improves the likelihood and the degree of conservativity. Hence, we propose to regularize the DSM objective to enforce satisfaction of the score FPE, and we show the effectiveness of this approach across various datasets.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2210.04296")

Code

Syntology Ran 5 of 14 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 2 ran · our draft was wrong; 3 ran with no contract checked.

By repository: official repository: 14 samples from 1 repository, 5 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

sony/fp-diffusion officialmentioned in papermentioned on GitHubjaxApache-2.0 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

14 samples harvested; 5 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

2ran · our draft was wrong
3ran
9unverified

Licence: 0 of the 14 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 sony/fp-diffusion. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

get_data_inverse_scaler sony/fp-diffusion/datasets.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 6c419026e778dee2 · report
get_data_scaler sony/fp-diffusion/datasets.py official repository ran · our draft was wrong Apache-2.0 (permissive) · 346d2e6cc8b48a5d · report
get_optimizer sony/fp-diffusion/losses.py official repository ran Apache-2.0 (permissive) · 8ff7c24dade9904c · report
optimization_manager sony/fp-diffusion/losses.py official repository ran Apache-2.0 (permissive) · 366bb8c7035a2fc8 · report
variance_scaling sony/fp-diffusion/models/layers.py official repository ran Apache-2.0 (permissive) · 3ac11bfe0ae80195 · report
batch_div sony/fp-diffusion/diff.py official repository unverified Apache-2.0 (permissive) · 93c2087126b99566 · report
classifier_fn_from_tfhub sony/fp-diffusion/evaluation.py official repository unverified Apache-2.0 (permissive) · 54a00db9aadf092f · report
crop_resize sony/fp-diffusion/datasets.py official repository unverified Apache-2.0 (permissive) · fd14d238ccd5f679 · report
get_act sony/fp-diffusion/models/layers.py official repository unverified Apache-2.0 (permissive) · db5f935a1d6b4c2c · report
get_div_fn sony/fp-diffusion/likelihood.py official repository unverified Apache-2.0 (permissive) · 0bfcb6b2d940e393 · report
gradient sony/fp-diffusion/diff.py official repository unverified Apache-2.0 (permissive) · 54eda5432a5725da · report
load_dataset_stats sony/fp-diffusion/evaluation.py official repository unverified Apache-2.0 (permissive) · b45ab263f8440954 · report
ncsn_conv1x1 sony/fp-diffusion/models/layers.py official repository unverified Apache-2.0 (permissive) · 85b2235eb7afaa4f · report
partial_t_j sony/fp-diffusion/diff.py official repository unverified Apache-2.0 (permissive) · 0c4a62d974bfda02 · report

Tasks

Denoising

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Denoising Score MatchingDiffusion

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