Papers › Progressive Skeletonization: Trimming more fat from a network at initialization

Progressive Skeletonization: Trimming more fat from a network at initialization

16 Jun 2020ICLR 2021 1arXiv:2006.09081archive 2025-07-28

Pau de Jorge, Amartya Sanyal, Harkirat S. Behl, Philip H. S. Torr, Gregory Rogez, Puneet K. Dokania

Recent studies have shown that skeletonization (pruning parameters) of networks at initialization provides all the practical benefits of sparsity both at inference and training time, while only marginally degrading their performance. However, we observe that beyond a certain level of sparsity (approx 95%), these approaches fail to preserve the network performance, and to our surprise, in many cases perform even worse than trivial random pruning. To this end, we propose an objective to find a skeletonized network with maximum foresight connection sensitivity (FORCE) whereby the trainability, in terms of connection sensitivity, of a pruned network is taken into consideration. We then propose two approximate procedures to maximize our objective (1) Iterative SNIP: allows parameters that were unimportant at earlier stages of skeletonization to become important at later stages; and (2) FORCE: iterative process that allows exploration by allowing already pruned parameters to resurrect at later stages of skeletonization. Empirical analyses on a large suite of experiments show that our approach, while providing at least as good a performance as other recent approaches on moderate pruning levels, provides remarkably improved performance on higher pruning levels (could remove up to 99.5% parameters while keeping the networks trainable). Code can be found in https://github.com/naver/force.

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 14 code samples harvested from 1 repository linked to this paper: 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 9 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 14 samples from 1 repository, 5 ran (5 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.

naver/force officialmentioned in papermentioned on GitHubpytorchMITSyntology: 14 samples, 5 ran (0 instrument-failed) · 9 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 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 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.

5ran
9unverified

Licence: 1 of the 14 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from naver/force. “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.

naver/force official repository 14 samples, 5 ran (0 instrument-failed) · 9 unverified
apply_prune_mask pruning/mask_networks.py ran MIT (permissive) · edda8bc5fb1dfa11 · report fixture: signature net:callable/0/?, keep_masks:list/1/Tensor, apply_hooks:bool/0/bool · returned list · level recorded 2026-09-25
get_mask in 119 papers
census: 9 implementations from 10 papers, 9 distinct outputs across 7 buckets, one shared input per bucket
pruning/pruning_algos.py ran MIT (permissive) · 3f216712b9e01cbb · report fixture: signature saliency:list/1/Tensor, pruning_factor:float/0/float · returned list · level recorded 2026-09-25
get_tiny_imagenet_train_valid_loader experiments/datasets.py ran MIT (permissive) · e5ca87502d56226e · report fixture: signature batch_size:int/0/int, augment:bool/0/bool, shuffle:bool/0/bool, num_workers:int/0/int · returned tuple · level recorded 2026-09-25
resnet18 in 432 papers experiments/models.py ran MIT (permissive) · 0327078528100688 · report fixture: signature temp:float/0/float, num_classes:int/0/int, in_planes:int/0/int, stable_resnet:bool/0/bool · returned ResNet · level recorded 2026-09-25
resnet34 in 148 papers experiments/models.py ran MIT (permissive) · 67cc5d9a1cd2e972 · report fixture: signature temp:float/0/float · returned ResNet · level recorded 2026-09-25
accuracy in 872 papers
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket
train_imagenet.py unverified MIT (permissive) here; the stored copy is pointer only · 9b8289076669fe4f · report
get_average_gradients pruning/pruning_algos.py unverified MIT (permissive) · c2fe2e0433a97c2a · report
get_average_saliencies pruning/pruning_algos.py unverified MIT (permissive) · a3aae03238435730 · report
get_cifar_test_loader experiments/datasets.py unverified MIT (permissive) · b6cbcb7ccb3e0a51 · report
get_cifar_train_valid_loader experiments/datasets.py unverified MIT (permissive) · 24854d716b08e3a5 · report
resnet50 in 121 papers experiments/models.py unverified MIT (permissive) · 881b8281d25db1b8 · report
validate in 313 papers train_imagenet.py unverified MIT (permissive) · 62eead0439dcfbc8 · report
vgg_cifar_experiment experiments/experiments.py unverified MIT (permissive) · 1cbecd8ff404af70 · report
vgg_tiny_imagenet_experiment experiments/experiments.py unverified MIT (permissive) · 472a885200c16eb7 · report

Tasks

Sensitivity

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