{"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/dataset-pruning","slug":"dataset-pruning","name":"Dataset Pruning","full_name":"Dataset Pruning","full_name_withheld":false,"description_markdown":"Dataset pruning is an approach to reduce a large dataset to obtain a small dataset by removing less significant sample.","description_state":"present","introduced_year":null,"introduced_by":{"title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","paper":"/paper/dataset-pruning-reducing-training-data-by","first_author":"Shuo Yang","n_authors":6,"url_abs":null,"archive_paper_url":"https://paperswithcode.com/paper/dataset-pruning-reducing-training-data-by"},"source":{"url":"https://arxiv.org/abs/2205.09329v2","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","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":25,"archive_num_papers":25,"papers_newest_first":[{"paper":null,"slug":"video-xl-pro-reconstructive-token-compression","title":"Video-XL-Pro: Reconstructive Token Compression for Extremely Long Video Understanding","date":"2025-03-24","arxiv_id":"2503.18478","n_code_links":0,"syntology":null},{"paper":"/paper/training-free-dataset-pruning-for-instance","slug":"training-free-dataset-pruning-for-instance","title":"Training-Free Dataset Pruning for Instance Segmentation","date":"2025-03-02","arxiv_id":"2503.00828","n_code_links":1,"syntology":{"ran":5,"of":8,"n_ran_checked":1,"n_instrument":4,"unverified":3,"pointer_only":8,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified","official":{"repos":["he-y/dataset-pruning-for-instance-segmentation"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/lightweight-dataset-pruning-without-full","slug":"lightweight-dataset-pruning-without-full","title":"Lightweight Dataset Pruning without Full Training via Example Difficulty and Prediction Uncertainty","date":"2025-02-10","arxiv_id":"2502.06905","n_code_links":1,"syntology":null},{"paper":"/paper/swift-cross-dataset-pruning-enhancing-fine","slug":"swift-cross-dataset-pruning-enhancing-fine","title":"Swift Cross-Dataset Pruning: Enhancing Fine-Tuning Efficiency in Natural Language Understanding","date":"2025-01-05","arxiv_id":"2501.02432","n_code_links":1,"syntology":null},{"paper":null,"slug":"video-set-distillation-information","title":"Video Set Distillation: Information Diversification and Temporal Densification","date":"2024-11-28","arxiv_id":"2412.00111","n_code_links":0,"syntology":null},{"paper":null,"slug":"data-lineage-inference-uncovering-privacy","title":"Data Lineage Inference: Uncovering Privacy Vulnerabilities of Dataset Pruning","date":"2024-11-24","arxiv_id":"2411.15796","n_code_links":0,"syntology":null},{"paper":"/paper/scan-bootstrapping-contrastive-pre-training","slug":"scan-bootstrapping-contrastive-pre-training","title":"SCAN: Bootstrapping Contrastive Pre-training for Data Efficiency","date":"2024-11-14","arxiv_id":"2411.09126","n_code_links":1,"syntology":null},{"paper":"/paper/gder-safeguarding-efficiency-balancing-and","slug":"gder-safeguarding-efficiency-balancing-and","title":"GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning","date":"2024-10-17","arxiv_id":"2410.13761","n_code_links":1,"syntology":{"ran":12,"of":18,"n_ran_checked":10,"n_instrument":2,"unverified":6,"pointer_only":18,"phrase":"12 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 6 unverified","official":{"repos":["ins1stenc3/gder"],"state":"official (archive's flag): 12 ran","n_ran":12,"n_constructed":4,"n_ran_no_instrument_failure":10,"n_unverified":6,"ran_from_kinds":["official"]}}},{"paper":null,"slug":"generalized-group-data-attribution","title":"Generalized Group Data Attribution","date":"2024-10-13","arxiv_id":"2410.09940","n_code_links":0,"syntology":null},{"paper":null,"slug":"sfprompt-communication-efficient-split","title":"SFPrompt: Communication-Efficient Split Federated Fine-Tuning for Large Pre-Trained Models over Resource-Limited Devices","date":"2024-07-24","arxiv_id":"2407.17533","n_code_links":0,"syntology":null},{"paper":"/paper/automatic-pruning-of-fine-tuning-datasets-for","slug":"automatic-pruning-of-fine-tuning-datasets-for","title":"Automatic Pruning of Fine-tuning Datasets for Transformer-based Language Models","date":"2024-07-11","arxiv_id":"2407.08887","n_code_links":1,"syntology":null},{"paper":"/paper/federated-learning-with-a-single-shared-image","slug":"federated-learning-with-a-single-shared-image","title":"Federated Learning with a Single Shared Image","date":"2024-06-18","arxiv_id":"2406.12658","n_code_links":1,"syntology":null},{"paper":null,"slug":"prunerf-segment-centric-dataset-pruning-via","title":"PruNeRF: Segment-Centric Dataset Pruning via 3D Spatial Consistency","date":"2024-06-02","arxiv_id":"2406.00798","n_code_links":0,"syntology":null},{"paper":null,"slug":"fairdedup-detecting-and-mitigating-vision","title":"FairDeDup: Detecting and Mitigating Vision-Language Fairness Disparities in Semantic Dataset Deduplication","date":"2024-04-24","arxiv_id":"2404.16123","n_code_links":0,"syntology":null},{"paper":null,"slug":"a-study-in-dataset-pruning-for-image-super","title":"A Study in Dataset Pruning for Image Super-Resolution","date":"2024-03-25","arxiv_id":"2403.17083","n_code_links":0,"syntology":null},{"paper":null,"slug":"exploring-learning-complexity-for-downstream","title":"Exploring Learning Complexity for Efficient Downstream Dataset Pruning","date":"2024-02-08","arxiv_id":"2402.05356","n_code_links":0,"syntology":null},{"paper":null,"slug":"dataset-difficulty-and-the-role-of-inductive","title":"Dataset Difficulty and the Role of Inductive Bias","date":"2024-01-03","arxiv_id":"2401.01867","n_code_links":0,"syntology":null},{"paper":null,"slug":"not-all-data-matters-an-end-to-end-adaptive","title":"Not All Data Matters: An End-to-End Adaptive Dataset Pruning Framework for Enhancing Model Performance and Efficiency","date":"2023-12-09","arxiv_id":"2312.05599","n_code_links":0,"syntology":null},{"paper":"/paper/spanning-training-progress-temporal-dual","slug":"spanning-training-progress-temporal-dual","title":"Spanning Training Progress: Temporal Dual-Depth Scoring (TDDS) for Enhanced Dataset Pruning","date":"2023-11-22","arxiv_id":"2311.13613","n_code_links":1,"syntology":{"ran":6,"of":11,"n_ran_checked":4,"n_instrument":2,"unverified":5,"pointer_only":1,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 5 unverified","official":{"repos":["zhangxin-xd/Dataset-Pruning-TDDS"],"state":"official (archive's flag): 6 ran","n_ran":6,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":5,"ran_from_kinds":["official"]}}},{"paper":"/paper/you-only-condense-once-two-rules-for-pruning-1","slug":"you-only-condense-once-two-rules-for-pruning-1","title":"You Only Condense Once: Two Rules for Pruning Condensed Datasets","date":"2023-10-21","arxiv_id":"2310.14019","n_code_links":1,"syntology":{"ran":13,"of":16,"n_ran_checked":5,"n_instrument":8,"unverified":3,"pointer_only":16,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified","official":{"repos":["he-y/you-only-condense-once"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":3,"ran_from_kinds":["official"]}}},{"paper":"/paper/sieve-multimodal-dataset-pruning-using-image","slug":"sieve-multimodal-dataset-pruning-using-image","title":"Sieve: Multimodal Dataset Pruning Using Image Captioning Models","date":"2023-10-03","arxiv_id":"2310.02110","n_code_links":1,"syntology":{"ran":2,"of":2,"n_ran_checked":0,"n_instrument":2,"unverified":0,"pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","official":{"repos":["facebookresearch/sieve"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"paper":"/paper/selectivity-drives-productivity-efficient","slug":"selectivity-drives-productivity-efficient","title":"Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning","date":"2023-09-21","arxiv_id":null,"n_code_links":1,"syntology":null},{"paper":"/paper/large-scale-dataset-pruning-with-dynamic","slug":"large-scale-dataset-pruning-with-dynamic","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","date":"2023-06-08","arxiv_id":"2306.05175","n_code_links":2,"syntology":{"ran":11,"of":11,"n_ran_checked":6,"n_instrument":5,"unverified":0,"pointer_only":7,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified","official":{"repos":["baai-dcai/dataset-pruning"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"paper":null,"slug":"clip-train-faster-with-less-data","title":"CLIP: Train Faster with Less Data","date":"2022-12-02","arxiv_id":"2212.01452","n_code_links":0,"syntology":null},{"paper":"/paper/dataset-pruning-reducing-training-data-by","slug":"dataset-pruning-reducing-training-data-by","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","date":"2022-05-19","arxiv_id":"2205.09329","n_code_links":0,"syntology":null}],"papers_shown":25,"papers_order":"date (newest first), then slug","paper_counts":{"archive_papers_tagged":25,"with_a_code_link":12,"where_syntology_ran_a_sample":6,"not_listed_spam_title":0,"listed":25,"listed_where_code_ran":6,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":5,"every_run_a_failure_of_syntologys_instrument":1,"listed_with_a_run_with_no_instrument_failure":5,"listed_every_run_a_failure_of_syntologys_instrument":1,"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":6,"papers_where_code_ran_first_page":"/method/dataset-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/dataset-pruning/papers/ran/1","json":"/method/dataset-pruning/papers/ran/1.json","rows":6}],"tasks":[{"task":"/task/diversity","name":"Diversity","papers":2},{"task":"/task/federated-learning","name":"Federated Learning","papers":2},{"task":"/task/image-classification","name":"Image Classification","papers":2},{"task":"/task/natural-language-understanding","name":"Natural Language Understanding","papers":2},{"task":"/task/image-classification","name":"image-classification","papers":2},{"task":null,"name":"8k","papers":1},{"task":"/task/all","name":"All","papers":1},{"task":"/task/classification-1","name":"Classification","papers":1},{"task":"/task/computational-efficiency","name":"Computational Efficiency","papers":1},{"task":"/task/dataset-condensation","name":"Dataset Condensation","papers":1},{"task":"/task/dataset-distillation","name":"Dataset Distillation","papers":1},{"task":"/task/density-estimation","name":"Density Estimation","papers":1},{"task":"/task/fairness","name":"Fairness","papers":1},{"task":null,"name":"GPU","papers":1},{"task":"/task/graph-embedding","name":"Graph Embedding","papers":1},{"task":"/task/image-captioning","name":"Image Captioning","papers":1},{"task":"/task/image-classification-with-label-noise","name":"Image Classification with Label Noise","papers":1},{"task":"/task/image-super-resolution","name":"Image Super-Resolution","papers":1},{"task":"/task/inductive-bias","name":"Inductive Bias","papers":1},{"task":"/task/informativeness","name":"Informativeness","papers":1}],"tasks_shown":20,"n_tasks":32,"usage_by_year":[{"year":"2022","papers":2},{"year":"2023","papers":6},{"year":"2024","papers":13},{"year":"2025","papers":4}],"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/dataset-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=Dataset%20Pruning","read_at":"2026-10-05T00:54:29+00:00","query":"Dataset Pruning","kind":"paper","have":"unknown_name","tier":null,"verified_implementation":null,"level":null,"level_meaning":"the served verification level, per answer; never summed across methods","resolved_to":null,"resolution":null,"resolved_name_differs":false,"absence_asserted":false,"absence_unchecked":null,"no_code_is_about_this_method":false,"subject":null,"archive_paper_arxiv_id":"2205.09329","repositories":null,"retrieve_with":null,"name_competition":{"verdict":"unresolved_bearers","may_be_wrong_sense":true,"bearers_found":2,"served":null,"leading_other_bearer":{"arxiv_id":"2205.09329","title":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","citations":186,"named_by":["title_prefix"],"bearer_name":"Dataset Pruning: Reducing Training Data by Examining Generalization Influence","ask_with":"have('2205.09329')"},"n_other_bearers_listed":2,"note":"Nothing resolved to 'Dataset Pruning' by name, but 2 thing(s) here DECLARE that name -- most cited: the paper 'Dataset Pruning: Reducing Training Data by Examining Generalization Influence' (arXiv:2205.09329, 186 citations). That is a RESOLUTION miss, not a coverage gap: the corpus holds the name under a spelling the lookup did not reach. Ask again with an entry of `also_named`."},"name_competition_text":"Nothing resolved to this name, but 2 entries in Syntology's graph carry it; the most cited is the paper “Dataset Pruning: Reducing Training Data by Examining Generalization Influence” (arXiv:2205.09329, 186 citations). The lookup reads this as a miss of its own name matching, not a gap in coverage: the graph holds the name under a spelling the lookup did not reach.","near_matches":["Training-Free Dataset Pruning (TFDP)","dataset","IG-Pruning","SFT dataset","ToM dataset","SFT dataset","KMA dataset","MCQ dataset"],"code_nearby":[],"code_nearby_caption":null,"origin_paper":null,"line":"name not resolved (unknown_name). Other entries in Syntology's graph carry this name; the lookup's note below says what that means for this name.","level_legend":null},"syntology_have_state":"loaded","record_sha256":"1460b4a8c0f543e6ace5f272ec766d16bb362b7eafb78efd8114dc8435e89cb6","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}