Papers › Diffused Redundancy in Pre-trained Representations

Diffused Redundancy in Pre-trained Representations

31 May 2023NeurIPS 2023 11arXiv:2306.00183archive 2025-07-28

Representations learned by pre-training a neural network on a large dataset are increasingly used successfully to perform a variety of downstream tasks. In this work, we take a closer look at how features are encoded in such pre-trained representations. We find that learned representations in a given layer exhibit a degree of diffuse redundancy, ie, any randomly chosen subset of neurons in the layer that is larger than a threshold size shares a large degree of similarity with the full layer and is able to perform similarly as the whole layer on a variety of downstream tasks. For example, a linear probe trained on 20% of randomly picked neurons from the penultimate layer of a ResNet50 pre-trained on ImageNet1k achieves an accuracy within 5% of a linear probe trained on the full layer of neurons for downstream CIFAR10 classification. We conduct experiments on different neural architectures (including CNNs and Transformers) pre-trained on both ImageNet1k and ImageNet21k and evaluate a variety of downstream tasks taken from the VTAB benchmark. We find that the loss and dataset used during pre-training largely govern the degree of diffuse redundancy and the "critical mass" of neurons needed often depends on the downstream task, suggesting that there is a task-inherent redundancy-performance Pareto frontier. Our findings shed light on the nature of representations learned by pre-trained deep neural networks and suggest that entire layers might not be necessary to perform many downstream tasks. We investigate the potential for exploiting this redundancy to achieve efficient generalization for downstream tasks and also draw caution to certain possible unintended consequences. Our code is available at https://github.com/nvedant07/diffused-redundancy.

PaperPDFConference PDFCodeCode 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 12 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: found in paper text by Syntology: 12 samples from 1 repository, 10 ran (10 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 2026-09-24 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

nvedant07/diffused-redundancy mentioned on GitHubpytorchSyntology: not harvested 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

12 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 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.

10ran
2unverified

Licence: 0 of the 12 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 nvedant07/STIR. “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.

nvedant07/STIR found in paper text by Syntology 12 samples, 10 ran (0 instrument-failed) · 2 unverified
add_args_to_parser stir/model/defaults.py ran Apache-2.0 (permissive) · 078da01e51a28471 · report fixture: signature arg_list:list/1/list, parser:ArgumentParser/0/? · returned ArgumentParser · level recorded 2026-09-24
centering in 17 papers stir/CKA_pytorch.py ran fingerprinted Apache-2.0 (permissive) · 3618a159ae4e6c6f · report fixture: signature K:Tensor/2/float · returned Tensor · level recorded 2026-09-26
forward_models stir/attack/losses.py ran Apache-2.0 (permissive) · b7b8027b897178e1 · report fixture: signature model:callable/0/?, inp:Tensor/2/float, layer_num:NoneType/0/? · returned Tensor · level recorded 2026-09-26
image_plot stir/plot_helper.py ran Apache-2.0 (permissive) · 38eecfafc4f839af · report fixture: signature image_object:ndarray/3/float, results_dir:str/0/str, filename:str/0/str, extension:str/0/str · returned str · level recorded 2026-09-26
kernel_HSIC in 9 papers
census: 3 implementations from 5 papers, 3 distinct outputs across 2 buckets, one shared input per bucket
stir/CKA_pytorch.py ran fingerprinted Apache-2.0 (permissive) · 1ed3811c7af7289d · report fixture: signature X:Tensor/2/float, Y:Tensor/2/float, sigma:float/0/float · returned Tensor · level recorded 2026-09-26
list_as_floats stir/helper.py ran Apache-2.0 (permissive) · 129b2365166bddfa · report fixture: signature arg:str/0/str · returned list · level recorded 2026-09-26
list_as_ints stir/helper.py ran Apache-2.0 (permissive) · eed7ebd73f4d076e · report fixture: signature arg:str/0/str · returned list · level recorded 2026-09-26
list_as_strs stir/helper.py ran fingerprinted Apache-2.0 (permissive) · fe88a8117264e87e · report fixture: signature arg:str/0/str · returned list · level recorded 2026-09-26
make_loaders stir/model/loaders.py ran Apache-2.0 (permissive) · 8de5a4001dbcbb38 · report fixture: signature workers:int/0/int, batch_size:int/0/int, transforms:tuple/1/callable, data_path:str/0/str, data_aug:bool/0/bool, custom_class:callable/0/?, dataset:str/0/str, label_mapping:NoneType/0/?, subset:NoneType/0/?, subset_type:str/0/str, subset_start:int/0/int, val_batch_size:NoneType/0/?, only_val:bool/0/bool, shuffle_train:bool/0/bool, shuffle_val:bool/0/bool, seed:int/0/int, custom_class_args:dict/0/?, n_classes:NoneType/0/?, n_samples:NoneType/0/?, pin_memory:bool/0/bool, return_datasets:bool/0/bool · returned tuple · level recorded 2026-09-26
rbf in 19 papers
census: 4 implementations from 6 papers, 3 distinct outputs across 3 buckets, one shared input per bucket
stir/CKA_pytorch.py ran fingerprinted Apache-2.0 (permissive) · 603a14d591c9dfb5 · report fixture: signature X:Tensor/2/float, sigma:NoneType/0/? · returned Tensor · level recorded 2026-09-26
TransformedLoader stir/model/loaders.py unverified Apache-2.0 (permissive) · e96e72db9f288269 · report
setup_args stir/model/train_model.py unverified Apache-2.0 (permissive) · 71f7ddd8aa721475 · report

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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