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 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="2003.03033")

Code

Syntology Ran 0 of 12 code samples harvested from 1 repository linked to this paper; 12 have no recorded run.

By repository: official repository: 12 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

jjgo/shrinkbench officialmentioned in papermentioned on GitHubpytorchMIT 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; 0 ran; 0 honoured the contract we drafted; 12 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.

12unverified

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. “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.

accuracy jjgo/shrinkbench/metrics/accuracy.py official repository unverified MIT (permissive) · b870f3841d427d99 · report
conv2d_flops jjgo/shrinkbench/metrics/abstract_flops.py official repository unverified MIT (permissive) · ea28692522bc6071 · report
correct jjgo/shrinkbench/metrics/accuracy.py official repository unverified MIT (permissive) · dae9edbccd1023f5 · report
dataset_path jjgo/shrinkbench/datasets/datasets.py official repository unverified MIT (permissive) · 1b4a7337eb8e904c · report
dense_flops jjgo/shrinkbench/metrics/abstract_flops.py official repository unverified MIT (permissive) · 6339375cb9607ec8 · report
get_classifier_module jjgo/shrinkbench/models/head.py official repository unverified MIT (permissive) · e5e70e38817af64f · report
mark_classifier jjgo/shrinkbench/models/head.py official repository unverified MIT (permissive) · d40ad3113b27ca66 · report
pretrained_weights jjgo/shrinkbench/models/pretrained.py official repository unverified MIT (permissive) · c4cd80b80f8cfb29 · report
reduce_linear_layer jjgo/shrinkbench/models/head.py official repository unverified MIT (permissive) · 3a12702023a2fdf5 · report
resnet_factory jjgo/shrinkbench/models/cifar_resnet.py official repository unverified MIT (permissive) · ad3e13d20798cd64 · report
vgg_bn_drop jjgo/shrinkbench/models/cifar_vgg.py official repository unverified MIT (permissive) · 898a6816feed8f15 · report
vgg_bn_drop_100 jjgo/shrinkbench/models/cifar_vgg.py official repository unverified MIT (permissive) · 3ee17008fcbc8808 · 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