Papers › Pruning-aware Sparse Regularization for Network Pruning

Pruning-aware Sparse Regularization for Network Pruning

18 Jan 2022arXiv:2201.06776archive 2025-07-28

Nanfei Jiang, Xu Zhao, Chaoyang Zhao, Yongqi An, Ming Tang, Jinqiao Wang

Structural neural network pruning aims to remove the redundant channels in the deep convolutional neural networks (CNNs) by pruning the filters of less importance to the final output accuracy. To reduce the degradation of performance after pruning, many methods utilize the loss with sparse regularization to produce structured sparsity. In this paper, we analyze these sparsity-training-based methods and find that the regularization of unpruned channels is unnecessary. Moreover, it restricts the network's capacity, which leads to under-fitting. To solve this problem, we propose a novel pruning method, named MaskSparsity, with pruning-aware sparse regularization. MaskSparsity imposes the fine-grained sparse regularization on the specific filters selected by a pruning mask, rather than all the filters of the model. Before the fine-grained sparse regularization of MaskSparity, we can use many methods to get the pruning mask, such as running the global sparse regularization. MaskSparsity achieves 63.03%-FLOPs reduction on ResNet-110 by removing 60.34% of the parameters, with no top-1 accuracy loss on CIFAR-10. On ILSVRC-2012, MaskSparsity reduces more than 51.07% FLOPs on ResNet-50, with only a loss of 0.76% in the top-1 accuracy. The code is released at https://github.com/CASIA-IVA-Lab/MaskSparsity. Moreover, we have integrated the code of MaskSparity into a PyTorch pruning toolkit, EasyPruner, at https://gitee.com/casia_iva_engineer/easypruner.

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, 1 violated, 10 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 11 samples that ran has no recorded date.

casia-iva-lab/masksparsity officialmentioned in paperpytorchMITSyntology: 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, 1 violated, 10 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.

1ran · violated contract
10ran
1unverified

Licence: 12 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 casia-iva-lab/masksparsity. “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.

casia-iva-lab/masksparsity official repository 12 samples, 11 ran (0 instrument-failed) · 1 unverified
is_number in 70 papers netslim/prune.py ran · violated contract MIT recorded; this copy not marked cleared · pointer only · 0fe9cf6c00ef56ea · report fixture: signature s:str/0/str · returned bool · level recorded, date not recorded
css_thresholding netslim/prune.py ran MIT recorded; this copy not marked cleared · pointer only · ecc0b3e3dba89e93 · report fixture: signature x:ndarray/1/float, percent:float/0/float, method:str/0/str · returned float64 · level recorded 2026-09-24
getBNmask netslim/display_BN.py ran MIT recorded; this copy not marked cleared · pointer only · 394cf43d44b2cc0a · report fixture: signature model:callable/0/?, norm_layer_names:list/1/str, ngpu:bool/0/bool, grad:bool/0/bool, mask:NoneType/0/?, uniform:float/0/float · returned dict · level recorded 2026-09-24
getBNmask_2 netslim/display_BN.py ran MIT recorded; this copy not marked cleared · pointer only · cf840cfd140abb9d · report fixture: signature model:callable/0/?, norm_layer_names:list/1/str, ngpu:bool/0/bool, grad:bool/0/bool, mask:NoneType/0/? · returned dict · level recorded 2026-09-24
get_model_complexity_info in 14 papers netslim/flops_counter.py ran MIT recorded; this copy not marked cleared · pointer only · fcc52c28bbf58580 · report fixture: signature model:callable/0/?, input_res:tuple/1/int, print_per_layer_stat:bool/0/bool, input_constructor:NoneType/0/? · returned tuple · level recorded 2026-09-24
get_model_parameters in 6 papers netslim/flops_counter.py ran MIT recorded; this copy not marked cleared · pointer only · e8d5c12b1b5e73d1 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-24
get_node_str netslim/graph_parser.py ran MIT recorded; this copy not marked cleared · pointer only · e3275daef46a7e57 · report fixture: signature node:MockNode/0/? · returned str · level recorded 2026-09-24
is_transposed netslim/prune.py ran MIT recorded; this copy not marked cleared · pointer only · f8e9003e1b6e70ef · report fixture: signature model:callable/0/?, data_name:str/0/str · returned bool · level recorded 2026-09-24
parse_module_name netslim/graph_parser.py ran MIT recorded; this copy not marked cleared · pointer only · 1a4afb2595c713b1 · report fixture: signature x:str/0/str · returned str · level recorded 2026-09-24
parse_output_name netslim/graph_parser.py ran MIT recorded; this copy not marked cleared · pointer only · b9289e5ca6f7928c · report fixture: signature x:str/0/str · returned str · level recorded 2026-09-24
rebuild netslim/rebuild.py ran MIT recorded; this copy not marked cleared · pointer only · d885639e3a40c3fd · report fixture: returned MinimalNet · level recorded 2026-09-24
get_model_flops in 7 papers netslim/flops_counter.py unverified MIT recorded; this copy not marked cleared · pointer only · a29e15a313b6243b · 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