{"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/effective-sparsification-of-neural-networks","title":"Effective Sparsification of Neural Networks with Global Sparsity Constraint","arxiv_id":"2105.01571","date":"2021-05-03","proceeding":"CVPR 2021 1","authors":["Xiao Zhou","Weizhong Zhang","Hang Xu","Tong Zhang"],"abstract":"Weight pruning is an effective technique to reduce the model size and inference time for deep neural networks in real-world deployments. However, since magnitudes and relative importance of weights are very different for different layers of a neural network, existing methods rely on either manual tuning or handcrafted heuristic rules to find appropriate pruning rates individually for each layer. This approach generally leads to suboptimal performance. In this paper, by directly working on the probability space, we propose an effective network sparsification method called {\\it probabilistic masking} (ProbMask), which solves a natural sparsification formulation under global sparsity constraint. The key idea is to use probability as a global criterion for all layers to measure the weight importance. An appealing feature of ProbMask is that the amounts of weight redundancy can be learned automatically via our constraint and thus we avoid the problem of tuning pruning rates individually for different layers in a network. Extensive experimental results on CIFAR-10/100 and ImageNet demonstrate that our method is highly effective, and can outperform previous state-of-the-art methods by a significant margin, especially in the high pruning rate situation. Notably, the gap of Top-1 accuracy between our ProbMask and existing methods can be up to 10\\%. As a by-product, we show ProbMask is also highly effective in identifying supermasks, which are subnetworks with high performance in a randomly weighted dense neural network.","url_abs":"https://arxiv.org/abs/2105.01571v1","url_pdf":"https://arxiv.org/pdf/2105.01571v1.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":"effective-sparsification-of-neural-networks","repo_url":"https://github.com/x-zho14/ProbMask-official","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/network-pruning-on-imagenet-resnet-50-90","task":"Network Pruning","dataset":"ImageNet - ResNet 50 - 90% sparsity","model":"ProbMask","rank_in_archive_order":6,"of":9,"metrics":{"Top-1 Accuracy":"74.68"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2105.01571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.01571"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/x-zho14/ProbMask-official","reach":null}],"summary":{"unverified":2},"by_repo_kind":{"official":{"samples":2,"ran":0,"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":2,"samples":[{"code_sha256_prefix":"9a080373e141816c","entry":"constrainScoreByWhole","repo":"x-zho14/ProbMask-official","repo_kind":"official","path":"utils/net_utils.py","file_url":"https://github.com/x-zho14/ProbMask-official/blob/HEAD/utils/net_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9a080373e141816c"}},{"code_sha256_prefix":"105c5143126167ba","entry":"solve_v_total","repo":"x-zho14/ProbMask-official","repo_kind":"official","path":"utils/net_utils.py","file_url":"https://github.com/x-zho14/ProbMask-official/blob/HEAD/utils/net_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"105c5143126167ba"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}