{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/method/movement-pruning","slug":"movement-pruning","name":"Movement Pruning","full_name":"Movement Pruning","full_name_withheld":false,"description_markdown":"**Movement Pruning** is a simple, deterministic first-order weight pruning method that is more adaptive to pretrained model fine-tuning. Magnitude pruning can be seen as utilizing zeroth-order information (absolute value) of the running model. In contrast, movement pruning methods are where importance is derived from first-order information. Intuitively, instead of selecting weights that are far from zero, we retain connections that are moving away from zero during the training process.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","paper":"/paper/movement-pruning-adaptive-sparsity-by-fine","first_author":"Victor Sanh","n_authors":3,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/movement-pruning-adaptive-sparsity-by-fine"},"source":{"url":"https://arxiv.org/abs/2005.07683v2","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","url_on_a_paper_host":true},"code_snippet_url":null,"code_snippet_url_on_a_code_host":false,"categories":[{"area":"General","area_id":"general","collection":"Pruning","url":"/methods/category/pruning","pwc_aliases":[]}],"n_papers_tagged":5,"archive_num_papers":5,"papers_newest_first":[{"paper":null,"slug":"2409-14162","title":"On Importance of Pruning and Distillation for Efficient Low Resource NLP","date":"2024-09-21","arxiv_id":"2409.14162","n_code_links":0,"syntology":null},{"paper":"/paper/pruning-meets-low-rank-parameter-efficient","slug":"pruning-meets-low-rank-parameter-efficient","title":"LoRAPrune: Structured Pruning Meets Low-Rank Parameter-Efficient Fine-Tuning","date":"2023-05-28","arxiv_id":"2305.18403","n_code_links":1,"syntology":{"ran":2,"of":5,"n_ran_checked":2,"n_instrument":0,"unverified":3,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified","official":{"repos":["aim-uofa/loraprune"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/what-matters-in-the-structured-pruning-of","slug":"what-matters-in-the-structured-pruning-of","title":"What Matters In The Structured Pruning of Generative Language Models?","date":"2023-02-07","arxiv_id":"2302.03773","n_code_links":1,"syntology":{"ran":2,"of":8,"n_ran_checked":2,"n_instrument":0,"unverified":6,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 6 unverified","official":{"repos":["huggingface/nn_pruning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":"/paper/block-pruning-for-faster-transformers","slug":"block-pruning-for-faster-transformers","title":"Block Pruning For Faster Transformers","date":"2021-09-10","arxiv_id":"2109.04838","n_code_links":1,"syntology":null},{"paper":"/paper/movement-pruning-adaptive-sparsity-by-fine","slug":"movement-pruning-adaptive-sparsity-by-fine","title":"Movement Pruning: Adaptive Sparsity by Fine-Tuning","date":"2020-05-15","arxiv_id":"2005.07683","n_code_links":4,"syntology":{"ran":4,"of":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"pointer_only":4,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","official":{"repos":["huggingface/transformers"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","unlocated"]}}}],"papers_shown":5,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":5,"with_a_code_link":4,"where_syntology_ran_a_sample":3,"not_listed_spam_title":0,"listed":5,"listed_where_code_ran":3,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":3,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":3,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"papers_where_code_ran":3,"papers_where_code_ran_first_page":"/method/movement-pruning/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not isolate this method inside it.","pages":[{"order":"ran","page":1,"of":1,"url":"/method/movement-pruning/papers/ran/1","json":"/method/movement-pruning/papers/ran/1.json","rows":3}],"tasks":[{"task":"/task/network-pruning","name":"Network Pruning","papers":2},{"task":"/task/document-classification","name":"Document Classification","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/knowledge-distillation","name":"Knowledge Distillation","papers":1},{"task":"/task/machine-translation","name":"Machine Translation","papers":1},{"task":"/task/model-compression","name":"Model Compression","papers":1},{"task":"/task/question-answering","name":"Question Answering","papers":1},{"task":"/task/text-classification","name":"Text Classification","papers":1},{"task":"/task/text-generation","name":"Text Generation","papers":1},{"task":"/task/transfer-learning","name":"Transfer Learning","papers":1},{"task":"/task/parameter-efficient-fine-tuning","name":"parameter-efficient fine-tuning","papers":1},{"task":"/task/text-classification-1","name":"text-classification","papers":1}],"tasks_shown":12,"n_tasks":12,"usage_by_year":[{"year":"2020","papers":1},{"year":"2021","papers":1},{"year":"2023","papers":2},{"year":"2024","papers":1}],"row_source":"methods_table","archive":{"source":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","archive_url":"https://paperswithcode.com/method/movement-pruning"},"syntology_read_at":"2026-10-05T00:36:11+00:00","syntology":{"source":"Syntology's have check for this name (the free coverage lookup), read from Syntology's graph","have_url":"https://syntology.ai/api/graph/have?x=Movement%20Pruning","read_at":"2026-10-05T00:59:19+00:00","query":"Movement Pruning","kind":"paper","have":"unverified_code","tier":"harvested","verified_implementation":false,"level":1,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":{"arxiv_id":"2005.07683"},"resolution":"paper","resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":"same_paper","archive_paper_arxiv_id":"2005.07683","repositories":{"listed":4,"in_graph":4,"list_truncated":false,"strongest_link":"official"},"retrieve_with":"get_harvested_code_for_paper(arxiv_id='2005.07683')","name_competition":{"verdict":"sole_bearer","may_be_wrong_sense":false,"bearers_found":1,"served":{"arxiv_id":"2005.07683","citations":637},"leading_other_bearer":null,"n_other_bearers_listed":0,"note":"Nothing else in this corpus is named 'Movement Pruning'. That is a statement about this corpus and not about the field: short names are reused, and a sense we never collected cannot show up here. Confirm `served.arxiv_id` if you had a specific paper in mind."},"name_competition_text":null,"near_matches":null,"code_nearby":[],"code_nearby_caption":null,"origin_paper":{"arxiv_id":"2005.07683","page":"/paper/movement-pruning-adaptive-sparsity-by-fine","syntology_url":"https://syntology.ai/paper/2005.07683","in_graph_layer":true,"samples":4,"ran":4,"n_ran_checked":3,"n_instrument":1,"unverified":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 3 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","instrument_means":"failures of Syntology's instrument, not of the code"},"line":"harvested code stored, below machine verification (unverified_code; harvested), served level V1. Repositories: 4 listed of 4 in the graph, strongest link: official. The lookup matched a paper by its title, arXiv:2005.07683, not a method entry. This answer is about arXiv:2005.07683, the paper the archive credits with this method.","level_legend":{"state":"quoted","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","card_sha256":"479785a84658dd682a11b10237b3620d651d7f87799f5dc7add970aaa83f6d39","note":"Syntology's served verification levels, quoted verbatim from its MCP server card; a row is split where the card separates clauses with a double hyphen, and the separator is not reproduced","levels":[{"level":"V0","quoted":["imports"]},{"level":"V1","quoted":["executes against a synthesized fixture and returns a value of the recorded type"]},{"level":"V2","quoted":["two implementations GENERATED from the paper's signature and spec agree numerically (1e-6) on fixture inputs","neither of the two ever read the authors' own code, so V2 measures how unambiguously the paper specifies the method, not fidelity to the authors' implementation (measured 2026-09-11, commit 75eaa77: cross_checked_by is a second LLM on 2,628 of 2,831 served samples)"]},{"level":"V3","quoted":["paper-derived property tests pass on both of those same two generations."]}],"no_rung":"No rung on this ladder compares the served code against the authors' implementation, so treat every level as evidence about runnability and internal agreement, not about matching the paper's results."}},"syntology_have_state":"loaded","record_sha256":"4098e3bce7b0219911d95927ae851e27b183e0003f19222d7f4b9e87dab2e274","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}