Papers › Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity

Connectivity Matters: Neural Network Pruning Through the Lens of Effective Sparsity

5 Jul 2021arXiv:2107.02306archive 2025-07-28

Artem Vysogorets, Julia Kempe

Neural network pruning is a fruitful area of research with surging interest in high sparsity regimes. Benchmarking in this domain heavily relies on faithful representation of the sparsity of subnetworks, which has been traditionally computed as the fraction of removed connections (direct sparsity). This definition, however, fails to recognize unpruned parameters that detached from input or output layers of underlying subnetworks, potentially underestimating actual effective sparsity: the fraction of inactivated connections. While this effect might be negligible for moderately pruned networks (up to 10-100 compression rates), we find that it plays an increasing role for thinner subnetworks, greatly distorting comparison between different pruning algorithms. For example, we show that effective compression of a randomly pruned LeNet-300-100 can be orders of magnitude larger than its direct counterpart, while no discrepancy is ever observed when using SynFlow for pruning [Tanaka et al., 2020]. In this work, we adopt the lens of effective sparsity to reevaluate several recent pruning algorithms on common benchmark architectures (e.g., LeNet-300-100, VGG-19, ResNet-18) and discover that their absolute and relative performance changes dramatically in this new and more appropriate framework. To aim for effective, rather than direct, sparsity, we develop a low-cost extension to most pruning algorithms. Further, equipped with effective sparsity as a reference frame, we partially reconfirm that random pruning with appropriate sparsity allocation across layers performs as well or better than more sophisticated algorithms for pruning at initialization [Su et al., 2020]. In response to this observation, using a simple analogy of pressure distribution in coupled cylinders from physics, we design novel layerwise sparsity quotas that outperform all existing baselines in the context of random pruning.

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: 8 ran (of which 0 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) · 4 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, 8 ran (8 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.

avysogorets/effective-sparsity officialmentioned in papermentioned on GitHubtfMITSyntology: 12 samples, 8 ran (0 instrument-failed) · 4 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: 8 ran (of which 0 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) · 4 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.

8ran
4unverified

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 avysogorets/effective-sparsity. “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.

avysogorets/effective-sparsity official repository 12 samples, 8 ran (0 instrument-failed) · 4 unverified
check_valid_sparsities utils.py ran MIT (permissive) · f5e1cacf2e574898 · report fixture: signature sparsities:list/1/float · returned ndarray · level recorded 2026-09-25
get_annotations_map tinyimagenet.py ran MIT (permissive) · 48d3eda95a1df7e6 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-25
get_direct_sparsity utils.py ran MIT (permissive) · f1e8db189aa50a91 · report fixture: signature matrices:list/1/ndarray · returned ndarray · level recorded 2026-09-25
get_overall_direct_sparsity utils.py ran MIT (permissive) · 234d756014c461ba · report fixture: signature matrices:list/1/ndarray · returned float64 · level recorded 2026-09-25
lamp pruning.py ran MIT (permissive) · 2af6c0698e3e005a · report fixture: signature weights:list/1/ndarray, target_sparsity:float/0/float · returned tuple · level recorded 2026-09-25
load_images in 48 papers tinyimagenet.py ran MIT (permissive) · 4ee899d1c4d39815 · report fixture: signature path:str/0/str, num_classes:int/0/int · returned tuple · level recorded 2026-09-25
magnitude_global pruning.py ran MIT (permissive) · 29761fa5e5cfbad7 · report fixture: signature weights:list/1/ndarray, target_sparsity:float/0/float · returned tuple · level recorded 2026-09-25
magnitude_layerwise pruning.py ran fingerprinted MIT (permissive) · 8e374b0bc371e7d3 · report fixture: signature weight:ndarray/2/float, target_sparsity:float/0/float · returned ndarray · level recorded 2026-09-25
effective_masks_custom effective_masks.py unverified MIT (permissive) · 388729982d8f315c · report
get_data in 223 papers data.py unverified MIT (permissive) · 515c5d29caa76c44 · report
get_model in 368 papers models.py unverified MIT (permissive) · 3c8c6de0284222a8 · report
stabilizer_synflow_layer effective_masks.py unverified MIT (permissive) · 62703c42dc5d39ab · report

Tasks

BenchmarkingNetwork Pruning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

PruningSNIPVGG-19

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