{"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/scop-scientific-control-for-reliable-neural","title":"SCOP: Scientific Control for Reliable Neural Network Pruning","arxiv_id":"2010.10732","date":"2020-10-21","proceeding":"NeurIPS 2020 12","authors":["Yehui Tang","Yunhe Wang","Yixing Xu","DaCheng Tao","Chunjing Xu","Chao Xu","Chang Xu"],"abstract":"This paper proposes a reliable neural network pruning algorithm by setting up a scientific control. Existing pruning methods have developed various hypotheses to approximate the importance of filters to the network and then execute filter pruning accordingly. To increase the reliability of the results, we prefer to have a more rigorous research design by including a scientific control group as an essential part to minimize the effect of all factors except the association between the filter and expected network output. Acting as a control group, knockoff feature is generated to mimic the feature map produced by the network filter, but they are conditionally independent of the example label given the real feature map. We theoretically suggest that the knockoff condition can be approximately preserved given the information propagation of network layers. Besides the real feature map on an intermediate layer, the corresponding knockoff feature is brought in as another auxiliary input signal for the subsequent layers. Redundant filters can be discovered in the adversarial process of different features. Through experiments, we demonstrate the superiority of the proposed algorithm over state-of-the-art methods. For example, our method can reduce 57.8% parameters and 60.2% FLOPs of ResNet-101 with only 0.01% top-1 accuracy loss on ImageNet. The code is available at https://github.com/huawei-noah/Pruning/tree/master/SCOP_NeurIPS2020.","url_abs":"https://arxiv.org/abs/2010.10732v2","url_pdf":"https://arxiv.org/pdf/2010.10732v2.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":"scop-scientific-control-for-reliable-neural","repo_url":"https://github.com/huawei-noah/Pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scop-scientific-control-for-reliable-neural","repo_url":"https://github.com/yehuitang/Pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"scop-scientific-control-for-reliable-neural","repo_url":"https://github.com/huawei-noah/Pruning/tree/master/SCOP_NeurIPS2020","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"pytorch","reach":null},{"paper_slug":"scop-scientific-control-for-reliable-neural","repo_url":"https://github.com/mindspore-ai/models/tree/master/research/cv/resnet50_adv_pruning","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"mindspore","reach":null}],"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/2010.10732","atlas_url":"https://app.syntology.ai/?focus=2010.10732","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.10732"}},"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":"deterministic:regex_extraction","url":"https://github.com/huawei-noah/Pruning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/mindspore-ai/models/tree/master/research/cv/resnet50_adv_pruning","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huawei-noah/Pruning/tree/master/SCOP_NeurIPS2020","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yehuitang/Pruning","reach":null}],"summary":{"ran":1},"by_repo_kind":{"official":{"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":"ca955ee5cd9a726b","entry":"Kf_Conv2d","repo":"huawei-noah/Pruning","repo_kind":"official","path":"SCOP_NeurIPS2020/pruning_modules.py","file_url":"https://github.com/huawei-noah/Pruning/blob/HEAD/SCOP_NeurIPS2020/pruning_modules.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"ca955ee5cd9a726b"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}