{"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/large-scale-dataset-pruning-with-dynamic","title":"Large-scale Dataset Pruning with Dynamic Uncertainty","arxiv_id":"2306.05175","date":"2023-06-08","proceeding":null,"authors":["Muyang He","Shuo Yang","Tiejun Huang","Bo Zhao"],"abstract":"The state of the art of many learning tasks, e.g., image classification, is advanced by collecting larger datasets and then training larger models on them. As the outcome, the increasing computational cost is becoming unaffordable. In this paper, we investigate how to prune the large-scale datasets, and thus produce an informative subset for training sophisticated deep models with negligible performance drop. We propose a simple yet effective dataset pruning method by exploring both the prediction uncertainty and training dynamics. We study dataset pruning by measuring the variation of predictions during the whole training process on large-scale datasets, i.e., ImageNet-1K and ImageNet-21K, and advanced models, i.e., Swin Transformer and ConvNeXt. Extensive experimental results indicate that our method outperforms the state of the art and achieves 25% lossless pruning ratio on both ImageNet-1K and ImageNet-21K. The code and pruned datasets are available at https://github.com/BAAI-DCAI/Dataset-Pruning.","url_abs":"https://arxiv.org/abs/2306.05175v3","url_pdf":"https://arxiv.org/pdf/2306.05175v3.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":"large-scale-dataset-pruning-with-dynamic","repo_url":"https://github.com/baai-dcai/dataset-pruning","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}},{"paper_slug":"large-scale-dataset-pruning-with-dynamic","repo_url":"https://github.com/prasangadhungel/Data-Pruning-with-Extrapolated-Scores","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"image-classification","task_name":"image-classification"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"convnext","method_name":"ConvNeXt"},{"method_slug":"dataset-pruning","method_name":"Dataset Pruning"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"pruning","method_name":"Pruning"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"stochastic-depth","method_name":"Stochastic Depth"},{"method_slug":"swin-transformer","method_name":"Swin Transformer"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2306.05175","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.05175"}},"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/prasangadhungel/Data-Pruning-with-Extrapolated-Scores","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/baai-dcai/dataset-pruning","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_draft_wrong":3,"ran_honours":1,"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":10,"ran":4,"repositories":1},"listed":{"samples":1,"ran":1,"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":1,"samples":[{"code_sha256_prefix":"2a80220dabcb742a","entry":"conv1x1","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/models/resnet.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2a80220dabcb742a"}},{"code_sha256_prefix":"600ff2c45e0de056","entry":"conv3x3","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/models/resnet.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/models/resnet.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"OUTPUT_MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"600ff2c45e0de056"}},{"code_sha256_prefix":"cea7a9f36bb84d97","entry":"evaluate","repo":"prasangadhungel/Data-Pruning-with-Extrapolated-Scores","repo_kind":"listed","path":"src/extrapolate/gnn_extrapolate.py","file_url":"https://github.com/prasangadhungel/Data-Pruning-with-Extrapolated-Scores/blob/HEAD/src/extrapolate/gnn_extrapolate.py","link_basis":"first_harvest_node","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"cea7a9f36bb84d97"}},{"code_sha256_prefix":"eec1e7cba51d5e8e","entry":"get_grad_norm","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/utils.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/utils.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eec1e7cba51d5e8e"}},{"code_sha256_prefix":"b33222a09fc93bec","entry":"set_weight_decay","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/optimizer.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/optimizer.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b33222a09fc93bec"}},{"code_sha256_prefix":"0c32459bef92ff8c","entry":"auto_resume_helper","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/utils.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/utils.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0c32459bef92ff8c"}},{"code_sha256_prefix":"22089fe7254c16b7","entry":"build_optimizer","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/optimizer.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/optimizer.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"22089fe7254c16b7"}},{"code_sha256_prefix":"7474e608a870c61a","entry":"build_scheduler","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/lr_scheduler.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/lr_scheduler.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7474e608a870c61a"}},{"code_sha256_prefix":"b0a5beb34716d5a6","entry":"check_keywords_in_name","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/optimizer.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/optimizer.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b0a5beb34716d5a6"}},{"code_sha256_prefix":"80450600f7f09b0a","entry":"create_logger","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/logger.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/logger.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"80450600f7f09b0a"}},{"code_sha256_prefix":"ea98019c31648879","entry":"load_checkpoint","repo":"baai-dcai/dataset-pruning","repo_kind":"official","path":"ImageNet/utils.py","file_url":"https://github.com/baai-dcai/dataset-pruning/blob/HEAD/ImageNet/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ea98019c31648879"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}