Papers › Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models

Unsupervised Representation Learning from Pre-trained Diffusion Probabilistic Models

26 Dec 2022arXiv:2212.12990archive 2025-07-28

Zijian Zhang, Zhou Zhao, Zhijie Lin

Diffusion Probabilistic Models (DPMs) have shown a powerful capacity of generating high-quality image samples. Recently, diffusion autoencoders (Diff-AE) have been proposed to explore DPMs for representation learning via autoencoding. Their key idea is to jointly train an encoder for discovering meaningful representations from images and a conditional DPM as the decoder for reconstructing images. Considering that training DPMs from scratch will take a long time and there have existed numerous pre-trained DPMs, we propose Pre-trained DPM AutoEncoding (PDAE), a general method to adapt existing pre-trained DPMs to the decoders for image reconstruction, with better training efficiency and performance than Diff-AE. Specifically, we find that the reason that pre-trained DPMs fail to reconstruct an image from its latent variables is due to the information loss of forward process, which causes a gap between their predicted posterior mean and the true one. From this perspective, the classifier-guided sampling method can be explained as computing an extra mean shift to fill the gap, reconstructing the lost class information in samples. These imply that the gap corresponds to the lost information of the image, and we can reconstruct the image by filling the gap. Drawing inspiration from this, we employ a trainable model to predict a mean shift according to encoded representation and train it to fill as much gap as possible, in this way, the encoder is forced to learn as much information as possible from images to help the filling. By reusing a part of network of pre-trained DPMs and redesigning the weighting scheme of diffusion loss, PDAE can learn meaningful representations from images efficiently. Extensive experiments demonstrate the effectiveness, efficiency and flexibility of PDAE.

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 Pre-trained DPM AutoEncoding (PDAE), 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). For this implementation, level 3 is recorded, but its report lists no property test that passed on both. No rung compares this code against the authors' implementation. For agents: get_reference_implementation(name='Pre-trained DPM AutoEncoding (PDAE)') (how to connect); the free check have('2212.12990') needs no token.

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

Code

Syntology 14 code samples harvested from 2 repositories linked to this paper: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 4 ran (3 with no instrument failure; 1 where Syntology's instrument failed); community (archive-listed): 4 samples from 1 repository, 1 ran (1 with no instrument failure; 0 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

ckczzj/pdae officialmentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 4 ran (1 instrument-failed) · 6 unverified report
GabrieleLozupone/LDAE mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
yue-zhongqi/diti mentioned on GitHubpytorchSyntology: 4 samples, 1 ran (0 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.

Code Syntology ran Syntology

14 samples harvested: 5 ran (of which 3 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · our draft was wrong
4ran
9unverified

Licence: 14 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 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.

ckczzj/pdae official repository 10 samples, 4 ran (1 instrument-failed) · 6 unverified
QKVAttention in 25 papers model/shift_unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · afd1425583888760 · report fixture: returned QKVAttention · level recorded 2026-09-22
QKVAttentionLegacy in 20 papers model/shift_unet.py ran · metamorphic tier: deterministic no licence file found · pointer only · ec9213c0c8138849 · report fixture: returned QKVAttentionLegacy · level recorded 2026-09-22
TimestepBlock in 11 papers model/shift_unet.py ran fingerprinted no licence file found · pointer only · 7778cda2e40a2497 · report fixture: signature x:Tensor/2/float, emb:Tensor/2/float · returned NoneType · level recorded 2026-09-24
normalization in 70 papers
census: 4 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
model/shift_unet.py ran · our draft was wrong no licence file found · pointer only · d5eb4721bd7ede86 · report fixture: signature channels:int/0/int · returned GroupNorm · level recorded 2026-09-22
AttentionBlock in 69 papers model/shift_unet.py unverified no licence file found · pointer only · b7379a086999f359 · report
ResBlockShift model/shift_unet.py unverified no licence file found · pointer only · cb9834d54ca93700 · report
ShiftUNet model/shift_unet.py unverified no licence file found · pointer only · 629e72d126a0dd83 · report
TimestepContextBlock model/shift_unet.py unverified no licence file found · pointer only · 76666159788ad649 · report
TimestepSequential model/shift_unet.py unverified no licence file found · pointer only · 546963d82095d48c · report
yue-zhongqi/diti community (archive-listed) 4 samples, 1 ran (0 instrument-failed) · 3 unverified
DDIM in 5 papers trainer/representation_learning_trainer.py ran no licence file found · pointer only · 580dc76645bca9ff · report fixture: returned DDIM · level recorded 2026-09-22
BaseTrainer in 16 papers trainer/representation_learning_trainer.py unverified no licence file found · pointer only · 4169604fb1fae5cb · report
GaussianDiffusion in 61 papers trainer/representation_learning_trainer.py unverified no licence file found · pointer only · efd4bc02cd02d1cf · report
RepresentationLearningTrainer trainer/representation_learning_trainer.py unverified no licence file found · pointer only · 3792fabf4fa7e452 · 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". 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 Pre-trained DPM AutoEncoding (PDAE) (graph method: Pre-trained DPM AutoEncoding (PDAE)), 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, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. Ran end-to-end against an independent peer; level 3 is recorded, but its report lists no property test that passed on both.

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

  1. ddpm_autoencoding_step entry · level 3 · ran · violated contract · 5c86f4ab085d6613e2224b67774c7fe3ac87c7ba9a505ddf93a8cfc6a4a825a9

2 sibling assemblies for Pre-trained DPM AutoEncoding (PDAE) (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for Pre-trained DPM AutoEncoding (PDAE) (graph method: Pre-trained DPM AutoEncoding (PDAE)). 17 bricks; individually on a fixture: 9 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. The assembly has not been run end-to-end.

one of 2 siblings

  1. ShiftUNet entry · level 0 · unverified · 629e72d126a0dd83
  2. AttentionBlock model · level 0 · unverified · b7379a086999f359
  3. ResBlock helper · level 0 · unverified · 6a2fbcc09ba19930
  4. ResBlockShift model · level 0 · unverified · cb9834d54ca93700
  5. TimestepSequential helper · level 0 · unverified · 546963d82095d48c
  6. conv_nd helper · level 0 · unverified · fe4eb545bbb728e0
  7. linear helper · level 1 · ran · our draft was wrong · 0e30585f04efffbe
  8. normalization helper · level 1 · ran · our draft was wrong · d5eb4721bd7ede86
  9. timestep_embedding helper · level 1 · ran · our draft was wrong · 270cd726f1952c2a
  10. zero_module helper · level 1 · ran · our draft was wrong · 129b804760b3115f
  11. QKVAttention helper · level 1 · ran · afd1425583888760
  12. QKVAttentionLegacy helper · level 1 · ran · ec9213c0c8138849
  13. Downsample model · level 1 · ran · 8c5676227adb2492
  14. TimestepBlock model · level 1 · ran · 7778cda2e40a2497
  15. Upsample model · level 1 · ran · 6998a3677700ee6c
  16. TimestepContextBlock model · level 0 · unverified · 76666159788ad649
  17. avg_pool_nd helper · level 0 · unverified · ecd0fc28815b65ae

harvested Assembly for Pre-trained DPM AutoEncoding (PDAE) (graph method: Pre-trained DPM AutoEncoding (PDAE)). 4 bricks; 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) · 3 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. RepresentationLearningTrainer entry · level 0 · unverified · 3792fabf4fa7e452
  2. BaseTrainer helper · level 0 · unverified · 4169604fb1fae5cb
  3. GaussianDiffusion helper · level 0 · unverified · efd4bc02cd02d1cf
  4. DDIM helper · level 1 · ran · 580dc76645bca9ff

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="2212.12990") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Image ReconstructionRepresentation Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusionfail

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