Papers › Hyper-Representations: Self-Supervised Representation Learning on Neural Network...

Hyper-Representations: Self-Supervised Representation Learning on Neural Network Weights for Model Characteristic Prediction

28 Oct 2021NeurIPS 2021 12arXiv:2110.15288archive 2025-07-28

Konstantin Schürholt, Dimche Kostadinov, Damian Borth

Self-Supervised Learning (SSL) has been shown to learn useful and information-preserving representations. Neural Networks (NNs) are widely applied, yet their weight space is still not fully understood. Therefore, we propose to use SSL to learn hyper-representations of the weights of populations of NNs. To that end, we introduce domain specific data augmentations and an adapted attention architecture. Our empirical evaluation demonstrates that self-supervised representation learning in this domain is able to recover diverse NN model characteristics. Further, we show that the proposed learned representations outperform prior work for predicting hyper-parameters, test accuracy, and generalization gap as well as transfer to out-of-distribution settings.

PaperPDFConference PDFCodeCode 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.

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

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 15 samples from 1 repository, 9 ran (9 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. 1 of the 9 samples that ran has no recorded date.

hsg-aiml/neurips_2021-weight_space_learning officialmentioned in paperpytorchSyntology: 15 samples, 9 ran (0 instrument-failed) · 6 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

15 samples harvested: 9 ran (of which 6 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 1 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 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 · violated contract
8ran
6unverified

Licence: 15 of the 15 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 hsg-aiml/neurips_2021-weight_space_learning. “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”. For 5 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

hsg-aiml/neurips_2021-weight_space_learning official repository 15 samples, 9 ran (0 instrument-failed) · 6 unverified
AE in 7 papers modules/model_definitions/def_simclr_ae_module.py ran no licence file found · pointer only · 46bd4536097074a2 · report fixture: signature x:Tensor/2/float · returned tuple · level recorded 2026-09-24
Decoder in 210 papers modules/model_definitions/def_simclr_ae_module.py ran · metamorphic tier: deterministic no licence file found · pointer only · 2c46d19912a394d0 · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers modules/model_definitions/def_simclr_ae_module.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8c1e454314c0328f · report fixture: returned Encoder · level recorded 2026-09-22
NT_Xent in 8 papers modules/model_definitions/def_simclr_ae_module.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1ab0b229f58bc5e7 · report fixture: returned NT_Xent · level recorded 2026-09-22
NT_Xent_pos modules/model_definitions/def_simclr_ae_module.py ran · metamorphic tier: deterministic no licence file found · pointer only · fef06fc631c15acb · report fixture: returned NT_Xent_pos · level recorded 2026-09-22
ProjectionHead in 10 papers modules/model_definitions/def_simclr_ae_module.py ran · metamorphic tier: deterministic no licence file found · pointer only · 726fa65b04e8959a · report fixture: returned ProjectionHead · level recorded 2026-09-22
ReconLoss modules/model_definitions/def_simclr_ae_module.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 5175c7399d3a091e · report fixture: returned ReconLoss · level recorded 2026-09-22
ResBlock in 127 papers
census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket
modules/model_definitions/def_simclr_ae_module.py ran no licence file found · pointer only · cad9c43c2ba56e9f · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
compute_outdim modules/model_definitions/def_net.py ran · violated contract no licence file found · pointer only · 47f26b184e0a12b8 · report fixture: signature i_dim:int/0/int, stride:int/0/int, kernel:int/0/int, padding:int/0/int, dilation:int/0/int · returned float · level recorded, date not recorded
AE_attn modules/model_definitions/def_simclr_ae_module.py unverified no licence file found · pointer only · 06892429dbe9ea1c · report
DecoderTransformer modules/model_definitions/def_simclr_ae_module.py unverified no licence file found · pointer only · 53c9fb5f84e680c5 · report
EncoderTransformer modules/model_definitions/def_simclr_ae_module.py unverified no licence file found · pointer only · d37df2bc77de97fa · report
GammaContrastReconLoss modules/model_definitions/def_simclr_ae_module.py unverified no licence file found · pointer only · 99c94955fd98d5dd · report
SimCLRAEModule modules/model_definitions/def_simclr_ae_module.py unverified no licence file found · pointer only · 99c404958aba899c · report
printProgressBar modules/model_definitions/def_simclr_ae_module.py unverified no licence file found · pointer only · a73e4907ef2d9664 · 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. 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.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Hyper-Representations (graph method: Hyper-Representations). 14 bricks; individually on a fixture: 8 ran (of which 6 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

  1. SimCLRAEModule entry · level 0 · unverified · 99c404958aba899c
  2. AE model · level 1 · ran · 46bd4536097074a2
  3. AE_attn model · level 0 · unverified · 06892429dbe9ea1c
  4. GammaContrastReconLoss loss · level 0 · unverified · 99c94955fd98d5dd
  5. printProgressBar helper · level 0 · unverified · a73e4907ef2d9664
  6. Decoder helper · level 1 · ran · 2c46d19912a394d0
  7. Encoder helper · level 1 · ran · 8c1e454314c0328f
  8. DecoderTransformer helper · level 0 · unverified · 53c9fb5f84e680c5
  9. EncoderTransformer helper · level 0 · unverified · d37df2bc77de97fa
  10. NT_Xent loss · level 1 · ran · 1ab0b229f58bc5e7
  11. NT_Xent_pos helper · level 1 · ran · fef06fc631c15acb
  12. ReconLoss loss · level 1 · ran · 5175c7399d3a091e
  13. ResBlock helper · level 1 · ran · cad9c43c2ba56e9f
  14. ProjectionHead helper · level 1 · ran · 726fa65b04e8959a

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="2110.15288") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Representation LearningSelf-Supervised Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Absolute Position EncodingsAttentionBPEContrastive Multiview CodingDense ConnectionsDropoutInfoNCELayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionTestTransformer

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