{"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,"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","title":"Training-Free Dataset Pruning for Instance Segmentation","date":"2025-03-02","arxiv_id":"2503.00828","n_code_links":1,"syntology":{"ran":4,"of":8,"unverified":4,"pointer_only":8}},{"paper":"/paper/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","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,"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,"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","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","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,"unverified":6,"pointer_only":18}},{"paper":null,"title":"Generalized Group Data Attribution","date":"2024-10-13","arxiv_id":"2410.09940","n_code_links":0,"syntology":null},{"paper":null,"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","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","title":"Federated Learning with a Single Shared Image","date":"2024-06-18","arxiv_id":"2406.12658","n_code_links":1,"syntology":null},{"paper":null,"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,"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,"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,"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,"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,"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","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,"unverified":5,"pointer_only":0}},{"paper":"/paper/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":12,"of":16,"unverified":4,"pointer_only":16}},{"paper":"/paper/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,"unverified":0,"pointer_only":0}},{"paper":"/paper/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","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","date":"2023-06-08","arxiv_id":"2306.05175","n_code_links":2,"syntology":{"ran":5,"of":11,"unverified":6,"pointer_only":1}},{"paper":null,"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","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,"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":"2026-09-24T18:15:14+00:00"}