{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/pruning-aware-sparse-regularization-for","title":"Pruning-aware Sparse Regularization for Network Pruning","arxiv_id":"2201.06776","date":"2022-01-18","proceeding":null,"authors":["Nanfei Jiang","Xu Zhao","Chaoyang Zhao","Yongqi An","Ming Tang","Jinqiao Wang"],"abstract":"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.","url_abs":"https://arxiv.org/abs/2201.06776v2","url_pdf":"https://arxiv.org/pdf/2201.06776v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"pruning-aware-sparse-regularization-for","repo_url":"https://github.com/casia-iva-lab/masksparsity","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2201.06776","atlas_url":"https://app.syntology.ai/?focus=2201.06776","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2201.06776"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/casia-iva-lab/masksparsity","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_violates":1,"ran":10,"unverified":1},"by_repo_kind":{"official":{"samples":12,"ran":11,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"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"},"n_pointer_only_for_licence":12,"samples":[{"code_sha256_prefix":"0fe9cf6c00ef56ea","entry":"is_number","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/prune.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/prune.py","link_basis":"harvester_set","language":"python","status":"ran_violates","verification_level":2,"contract_check":"VIOLATES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"0fe9cf6c00ef56ea"}},{"code_sha256_prefix":"ecc0b3e3dba89e93","entry":"css_thresholding","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/prune.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/prune.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"ecc0b3e3dba89e93"}},{"code_sha256_prefix":"394cf43d44b2cc0a","entry":"getBNmask","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/display_BN.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/display_BN.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"394cf43d44b2cc0a"}},{"code_sha256_prefix":"cf840cfd140abb9d","entry":"getBNmask_2","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/display_BN.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/display_BN.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"cf840cfd140abb9d"}},{"code_sha256_prefix":"fcc52c28bbf58580","entry":"get_model_complexity_info","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/flops_counter.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/flops_counter.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"fcc52c28bbf58580"}},{"code_sha256_prefix":"e8d5c12b1b5e73d1","entry":"get_model_parameters","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/flops_counter.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/flops_counter.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e8d5c12b1b5e73d1"}},{"code_sha256_prefix":"e3275daef46a7e57","entry":"get_node_str","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/graph_parser.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/graph_parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"e3275daef46a7e57"}},{"code_sha256_prefix":"f8e9003e1b6e70ef","entry":"is_transposed","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/prune.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/prune.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"f8e9003e1b6e70ef"}},{"code_sha256_prefix":"1a4afb2595c713b1","entry":"parse_module_name","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/graph_parser.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/graph_parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"1a4afb2595c713b1"}},{"code_sha256_prefix":"b9289e5ca6f7928c","entry":"parse_output_name","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/graph_parser.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/graph_parser.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"b9289e5ca6f7928c"}},{"code_sha256_prefix":"d885639e3a40c3fd","entry":"rebuild","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/rebuild.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/rebuild.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"d885639e3a40c3fd"}},{"code_sha256_prefix":"a29e15a313b6243b","entry":"get_model_flops","repo":"casia-iva-lab/masksparsity","repo_kind":"official","path":"netslim/flops_counter.py","file_url":"https://github.com/casia-iva-lab/masksparsity/blob/HEAD/netslim/flops_counter.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":false,"mcp_get_code":{"code_sha256":"a29e15a313b6243b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}