{"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/structured-pruning-adapters","title":"Structured Pruning Adapters","arxiv_id":"2211.10155","date":"2022-11-17","proceeding":null,"authors":["Lukas Hedegaard","Aman Alok","Juby Jose","Alexandros Iosifidis"],"abstract":"Adapters are a parameter-efficient alternative to fine-tuning, which augment a frozen base network to learn new tasks. Yet, the inference of the adapted model is often slower than the corresponding fine-tuned model. To improve on this, we propose Structured Pruning Adapters (SPAs), a family of compressing, task-switching network adapters, that accelerate and specialize networks using tiny parameter sets and structured pruning. Specifically, we propose a channel-based SPA and evaluate it with a suite of pruning methods on multiple computer vision benchmarks. Compared to regular structured pruning with fine-tuning, our channel-SPAs improve accuracy by 6.9% on average while using half the parameters at 90% pruned weights. Alternatively, they can learn adaptations with 17x fewer parameters at 70% pruning with 1.6% lower accuracy. Similarly, our block-SPA requires far fewer parameters than pruning with fine-tuning. Our experimental code and Python library of adapters are available at github.com/lukashedegaard/structured-pruning-adapters.","url_abs":"https://arxiv.org/abs/2211.10155v3","url_pdf":"https://arxiv.org/pdf/2211.10155v3.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":"structured-pruning-adapters","repo_url":"https://github.com/lukashedegaard/structured-pruning-adapters","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"single-particle-analysis","task_name":"Single Particle Analysis"}],"methods":[{"method_slug":"base","method_name":"BASE"},{"method_slug":null,"method_name":"Library"},{"method_slug":"pruning","method_name":"Pruning"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2211.10155","atlas_url":"https://app.syntology.ai/?focus=2211.10155","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2211.10155"}},"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/lukashedegaard/structured-pruning-adapters","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran":2},"by_repo_kind":{"official":{"samples":2,"ran":2,"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":"b408fc9c1069786e","entry":"bkron","repo":"lukashedegaard/structured-pruning-adapters","repo_kind":"official","path":"sp_adapters/utils.py","file_url":"https://github.com/lukashedegaard/structured-pruning-adapters/blob/HEAD/sp_adapters/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b408fc9c1069786e"}},{"code_sha256_prefix":"caf5487bfbb58b14","entry":"recursive_replace","repo":"lukashedegaard/structured-pruning-adapters","repo_kind":"official","path":"sp_adapters/utils.py","file_url":"https://github.com/lukashedegaard/structured-pruning-adapters/blob/HEAD/sp_adapters/utils.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"caf5487bfbb58b14"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}