{"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/blockswap-fisher-guided-block-substitution","title":"BlockSwap: Fisher-guided Block Substitution for Network Compression on a Budget","arxiv_id":"1906.04113","date":"2019-06-10","proceeding":"ICLR 2020 1","authors":["Jack Turner","Elliot J. Crowley","Michael O'Boyle","Amos Storkey","Gavin Gray"],"abstract":"The desire to map neural networks to varying-capacity devices has led to the development of a wealth of compression techniques, many of which involve replacing standard convolutional blocks in a large network with cheap alternative blocks. However, not all blocks are created equally; for a required compute budget there may exist a potent combination of many different cheap blocks, though exhaustively searching for such a combination is prohibitively expensive. In this work, we develop BlockSwap: a fast algorithm for choosing networks with interleaved block types by passing a single minibatch of training data through randomly initialised networks and gauging their Fisher potential. These networks can then be used as students and distilled with the original large network as a teacher. We demonstrate the effectiveness of the chosen networks across CIFAR-10 and ImageNet for classification, and COCO for detection, and provide a comprehensive ablation study of our approach. BlockSwap quickly explores possible block configurations using a simple architecture ranking system, yielding highly competitive networks in orders of magnitude less time than most architecture search techniques (e.g. under 5 minutes on a single GPU for CIFAR-10). Code is available at https://github.com/BayesWatch/pytorch-blockswap.","url_abs":"https://arxiv.org/abs/1906.04113v2","url_pdf":"https://arxiv.org/pdf/1906.04113v2.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":"blockswap-fisher-guided-block-substitution","repo_url":"https://github.com/BayesWatch/pytorch-blockswap","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":null},{"paper_slug":"blockswap-fisher-guided-block-substitution","repo_url":"https://github.com/Vini90/pytorch-BlockSwap-InferenceTime","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":null,"task_name":"GPU"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=1906.04113","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1906.04113"}},"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/BayesWatch/pytorch-blockswap","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/Vini90/pytorch-BlockSwap-InferenceTime","reach":{"status":"ok"}}],"summary":{"ran_honours":2,"ran_violates":1},"by_repo_kind":{"official":{"samples":3,"ran":3,"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":0,"samples":[{"code_sha256_prefix":"7556a5bddc992e63","entry":"at","repo":"BayesWatch/pytorch-blockswap","repo_kind":"official","path":"utils.py","file_url":"https://github.com/BayesWatch/pytorch-blockswap/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7556a5bddc992e63"}},{"code_sha256_prefix":"9620e20bbcbbb1d0","entry":"at_loss","repo":"BayesWatch/pytorch-blockswap","repo_kind":"official","path":"utils.py","file_url":"https://github.com/BayesWatch/pytorch-blockswap/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"9620e20bbcbbb1d0"}},{"code_sha256_prefix":"f6484efda3ef4ceb","entry":"distillation","repo":"BayesWatch/pytorch-blockswap","repo_kind":"official","path":"utils.py","file_url":"https://github.com/BayesWatch/pytorch-blockswap/blob/HEAD/utils.py","link_basis":"first_harvest_node","language":"python","status":"ran_violates","verification_level":1,"contract_check":"VIOLATES","metamorphic_tier":"invariant","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"f6484efda3ef4ceb"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}