Papers › What is the State of Neural Network Pruning?

What is the State of Neural Network Pruning?

6 Mar 2020arXiv:2003.03033archive 2025-07-28

Davis Blalock, Jose Javier Gonzalez Ortiz, Jonathan Frankle, John Guttag

Neural network pruning---the task of reducing the size of a network by removing parameters---has been the subject of a great deal of work in recent years. We provide a meta-analysis of the literature, including an overview of approaches to pruning and consistent findings in the literature. After aggregating results across 81 papers and pruning hundreds of models in controlled conditions, our clearest finding is that the community suffers from a lack of standardized benchmarks and metrics. This deficiency is substantial enough that it is hard to compare pruning techniques to one another or determine how much progress the field has made over the past three decades. To address this situation, we identify issues with current practices, suggest concrete remedies, and introduce ShrinkBench, an open-source framework to facilitate standardized evaluations of pruning methods. We use ShrinkBench to compare various pruning techniques and show that its comprehensive evaluation can prevent common pitfalls when comparing pruning methods.

PaperPDFCodeCode 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: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 12 samples from 1 repository, 11 ran (11 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 on 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

jjgo/shrinkbench officialmentioned in papermentioned on GitHubpytorchMITSyntology: 12 samples, 11 ran (0 instrument-failed) · 1 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

12 samples harvested: 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 1 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.

11ran
1unverified

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 jjgo/shrinkbench. “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.

jjgo/shrinkbench official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
metrics/accuracy.py ran MIT (permissive) · b870f3841d427d99 · report fixture: signature model:callable/0/?, dataloader:SimpleDataLoader/0/?, topk:tuple/1/int · returned ndarray · level recorded 2026-09-25
conv2d_flops metrics/abstract_flops.py ran MIT (permissive) · ea28692522bc6071 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, input_shape:tuple/1/int, kernel_shape:tuple/1/int, padding:str/0/str, strides:tuple/1/int, dilation:int/0/int · returned int · level recorded 2026-09-25
correct in 5 papers metrics/accuracy.py ran MIT (permissive) · dae9edbccd1023f5 · report fixture: signature output:Tensor/2/float, target:Tensor/1/int, topk:tuple/1/int · returned list · level recorded 2026-09-25
dataset_path datasets/datasets.py ran MIT (permissive) · 1b4a7337eb8e904c · report fixture: signature dataset:str/0/str, path:str/0/str · returned PosixPath · level recorded 2026-09-25
dense_flops metrics/abstract_flops.py ran fingerprinted MIT (permissive) · 6339375cb9607ec8 · report fixture: signature in_neurons:int/0/int, out_neurons:int/0/int · returned int · level recorded 2026-09-25
get_classifier_module models/head.py ran MIT (permissive) · e5e70e38817af64f · report fixture: signature model:callable/0/? · returned Linear · level recorded 2026-09-25
mark_classifier models/head.py ran MIT (permissive) · d40ad3113b27ca66 · report fixture: signature model:callable/0/? · returned ResNet · level recorded 2026-09-25
reduce_linear_layer models/head.py ran MIT (permissive) · 3a12702023a2fdf5 · report fixture: signature layer:callable/0/?, n_classes:int/0/int, keep_weights:bool/0/bool · returned Linear · level recorded 2026-09-25
resnet_factory models/cifar_resnet.py ran MIT (permissive) · ad3e13d20798cd64 · report fixture: signature filters:list/1/int, num_classes:int/0/int, name:str/0/str · returned function · level recorded 2026-09-25
vgg_bn_drop models/cifar_vgg.py ran MIT (permissive) · 898a6816feed8f15 · report fixture: signature pretrained:bool/0/bool · returned VGGBnDrop · level recorded 2026-09-25
vgg_bn_drop_100 models/cifar_vgg.py ran MIT (permissive) · 3ee17008fcbc8808 · report fixture: signature pretrained:bool/0/bool · returned VGGBnDrop · level recorded 2026-09-25
pretrained_weights models/pretrained.py unverified MIT (permissive) · c4cd80b80f8cfb29 · report

Tasks

Network Pruning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Pruning

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