{"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/sparse-training-via-boosting-pruning","title":"Sparse Training via Boosting Pruning Plasticity with Neuroregeneration","arxiv_id":"2106.10404","date":"2021-06-19","proceeding":"NeurIPS 2021 12","authors":["Shiwei Liu","Tianlong Chen","Xiaohan Chen","Zahra Atashgahi","Lu Yin","Huanyu Kou","Li Shen","Mykola Pechenizkiy","Zhangyang Wang","Decebal Constantin Mocanu"],"abstract":"Works on lottery ticket hypothesis (LTH) and single-shot network pruning (SNIP) have raised a lot of attention currently on post-training pruning (iterative magnitude pruning), and before-training pruning (pruning at initialization). The former method suffers from an extremely large computation cost and the latter usually struggles with insufficient performance. In comparison, during-training pruning, a class of pruning methods that simultaneously enjoys the training/inference efficiency and the comparable performance, temporarily, has been less explored. To better understand during-training pruning, we quantitatively study the effect of pruning throughout training from the perspective of pruning plasticity (the ability of the pruned networks to recover the original performance). Pruning plasticity can help explain several other empirical observations about neural network pruning in literature. We further find that pruning plasticity can be substantially improved by injecting a brain-inspired mechanism called neuroregeneration, i.e., to regenerate the same number of connections as pruned. We design a novel gradual magnitude pruning (GMP) method, named gradual pruning with zero-cost neuroregeneration (\\textbf{GraNet}), that advances state of the art. Perhaps most impressively, its sparse-to-sparse version for the first time boosts the sparse-to-sparse training performance over various dense-to-sparse methods with ResNet-50 on ImageNet without extending the training time. We release all codes in https://github.com/Shiweiliuiiiiiii/GraNet.","url_abs":"https://arxiv.org/abs/2106.10404v4","url_pdf":"https://arxiv.org/pdf/2106.10404v4.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":"sparse-training-via-boosting-pruning","repo_url":"https://github.com/Shiweiliuiiiiiii/GraNet","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}},{"paper_slug":"sparse-training-via-boosting-pruning","repo_url":"https://github.com/vita-group/granet","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"network-pruning","task_name":"Network Pruning"},{"task_slug":"sparse-learning","task_name":"Sparse Learning"}],"methods":[{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/sparse-learning-on-imagenet","task":"Sparse Learning","dataset":"ImageNet","model":"Resnet-50: 80% Sparse 100 epochs","rank_in_archive_order":3,"of":9,"metrics":{"Top-1 Accuracy":"76"},"uses_additional_data":false},{"leaderboard":"/sota/sparse-learning-on-imagenet","task":"Sparse Learning","dataset":"ImageNet","model":"Resnet-50: 90% Sparse 100 epochs","rank_in_archive_order":5,"of":9,"metrics":{"Top-1 Accuracy":"74.5"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.10404","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.10404"}},"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":"deterministic:regex_extraction","url":"https://github.com/Shiweiliuiiiiiii/GraNet","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/vita-group/granet","reach":null}],"summary":{"ran":1},"by_repo_kind":{"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"21c612263568ab05","entry":"Masking","repo":"vita-group/granet","repo_kind":"listed","path":"CIFAR/sparselearning/core.py","file_url":"https://github.com/vita-group/granet/blob/HEAD/CIFAR/sparselearning/core.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"21c612263568ab05"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}