{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T18:06:21Z","timestamp":1781114781850,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T00:00:00Z","timestamp":1777507200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.patcog.2026.113730","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T06:48:40Z","timestamp":1776926920000},"page":"113730","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PD","title":["A unified analysis on cross-architecture generalizability of coresets"],"prefix":"10.1016","volume":"179","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9341-8937","authenticated-orcid":false,"given":"Diqi","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Frank","family":"de Hoog","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brano","family":"Kusy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5822-8233","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongsheng","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patcog.2026.113730_b1","series-title":"CVPR","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patcog.2026.113730_b2","series-title":"ICCV","first-page":"10012","article-title":"Swin transformer: Hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.patcog.2026.113730_b3","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.107899","article-title":"Pruning by explaining: A novel criterion for deep neural network pruning","volume":"115","author":"Yeom","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113730_b4","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107468","article-title":"Goal driven network pruning for object recognition","volume":"110","author":"Kaplan","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113730_b5","series-title":"ICLR","article-title":"Moderate coreset: A universal method of data selection for real-world data-efficient deep learning","author":"Xia","year":"2022"},{"key":"10.1016\/j.patcog.2026.113730_b6","first-page":"19523","article-title":"Beyond neural scaling laws: beating power law scaling via data pruning","volume":"vol. 35","author":"Sorscher","year":"2022"},{"key":"10.1016\/j.patcog.2026.113730_b7","series-title":"ICLR","article-title":"Coverage-centric coreset selection for high pruning rates","author":"Zheng","year":"2023"},{"issue":"55","key":"10.1016\/j.patcog.2026.113730_b8","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"Elsken","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113730_b9","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111948","article-title":"DDS-NAS: Dynamic data selection within neural architecture search via on-line hard example mining applied to image classification","volume":"169","author":"Poyser","year":"2026","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113730_b10","article-title":"Active learning with statistical models","volume":"vol. 7","author":"Cohn","year":"1994"},{"issue":"Nov","key":"10.1016\/j.patcog.2026.113730_b11","first-page":"45","article-title":"Support vector machine active learning with applications to text classification","volume":"2","author":"Tong","year":"2001","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.patcog.2026.113730_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110385","article-title":"BALQUE: Batch active learning by querying unstable examples with calibrated confidence","volume":"151","author":"Han","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113730_b13","series-title":"ICML","article-title":"Mind the boundary: Coreset selection via reconstructing the decision boundary","author":"Yang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113730_b14","first-page":"17044","article-title":"Identifying mislabeled data using the area under the margin ranking","volume":"vol. 33","author":"Pleiss","year":"2020"},{"key":"10.1016\/j.patcog.2026.113730_b15","first-page":"181","article-title":"DeepCore: A comprehensive library for coreset selection in deep learning","author":"Guo","year":"2022","journal-title":"Int. Conf. Database Expert. Syst. Appl."},{"key":"10.1016\/j.patcog.2026.113730_b16","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.patcog.2026.113730_b17","series-title":"CVPR","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"10.1016\/j.patcog.2026.113730_b18","first-page":"24261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume":"vol. 34","author":"Tolstikhin","year":"2021"},{"key":"10.1016\/j.patcog.2026.113730_b19","first-page":"9912","article-title":"Unsupervised learning of visual features by contrasting cluster assignments","volume":"vol. 33","author":"Caron","year":"2020"},{"key":"10.1016\/j.patcog.2026.113730_b20","series-title":"An empirical study of example forgetting during deep neural network learning","author":"Toneva","year":"2018"},{"key":"10.1016\/j.patcog.2026.113730_b21","series-title":"ICML","first-page":"1121","article-title":"Herding dynamical weights to learn","author":"Welling","year":"2009"},{"key":"10.1016\/j.patcog.2026.113730_b22","article-title":"Cognition-driven structural prior for instance-dependent label transition matrix estimation","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.113730_b23","series-title":"CVPR","first-page":"248","article-title":"ImageNet: A large-scale hierarchical image database","author":"Deng","year":"2009"},{"key":"10.1016\/j.patcog.2026.113730_b24","series-title":"ECCV","first-page":"116","article-title":"ShuffleNet V2: Practical guidelines for efficient cnn architecture design","author":"Ma","year":"2018"},{"key":"10.1016\/j.patcog.2026.113730_b25","series-title":"ICML","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"10.1016\/j.patcog.2026.113730_b26","series-title":"ECCV","first-page":"68","article-title":"TinyViT: Fast pretraining distillation for small vision transformers","author":"Wu","year":"2022"},{"key":"10.1016\/j.patcog.2026.113730_b27","series-title":"CVPR","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"10.1016\/j.patcog.2026.113730_b28","series-title":"ICLR","article-title":"Selection via proxy: Efficient data selection for deep learning","author":"Coleman","year":"2020"},{"key":"10.1016\/j.patcog.2026.113730_b29","series-title":"ICLR","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2015"},{"key":"10.1016\/j.patcog.2026.113730_b30","series-title":"CVPR","first-page":"4510","article-title":"MobileNetV2: Inverted residuals and linear bottlenecks","author":"Sandler","year":"2018"},{"issue":"1","key":"10.1016\/j.patcog.2026.113730_b31","first-page":"1","article-title":"Geometric approximation via coresets","volume":"52","author":"Agarwal","year":"2005","journal-title":"Comb. Comput. Geom."},{"key":"10.1016\/j.patcog.2026.113730_b32","doi-asserted-by":"crossref","unstructured":"S. Har-Peled, S. Mazumdar, On coresets for k-means and k-median clustering, in: Proceedings of the Thirty-Sixth Annual ACM Symposium on Theory of Computing, 2004, pp. 291\u2013300.","DOI":"10.1145\/1007352.1007400"},{"key":"10.1016\/j.patcog.2026.113730_b33","doi-asserted-by":"crossref","unstructured":"D. Feldman, M. Langberg, A unified framework for approximating and clustering data, in: Proceedings of the Forty-third Annual ACM Symposium on Theory of Computing, 2011, pp. 569\u2013578.","DOI":"10.1145\/1993636.1993712"},{"key":"10.1016\/j.patcog.2026.113730_b34","series-title":"Practical coreset constructions for machine learning","author":"Bachem","year":"2017"},{"key":"10.1016\/j.patcog.2026.113730_b35","first-page":"22934","article-title":"Near-optimal k-clustering in the sliding window model","volume":"vol. 36","author":"Woodruff","year":"2023"},{"key":"10.1016\/j.patcog.2026.113730_b36","article-title":"On coresets for logistic regression","volume":"vol. 31","author":"Munteanu","year":"2018"},{"key":"10.1016\/j.patcog.2026.113730_b37","series-title":"Maximum margin coresets for active and noise tolerant learning","author":"Har-Peled","year":"2006"},{"key":"10.1016\/j.patcog.2026.113730_b38","first-page":"30352","article-title":"Coresets for decision trees of signals","volume":"vol. 34","author":"Jubran","year":"2021"},{"key":"10.1016\/j.patcog.2026.113730_b39","first-page":"2881","article-title":"What neural networks memorize and why: Discovering the long tail via influence estimation","volume":"vol. 33","author":"Feldman","year":"2020"},{"key":"10.1016\/j.patcog.2026.113730_b40","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume":"vol. 34","author":"Paul","year":"2021"},{"key":"10.1016\/j.patcog.2026.113730_b41","series-title":"CVPR","first-page":"26223","article-title":"Spanning training progress: Temporal dual-depth scoring (TDDS) for enhanced dataset pruning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.patcog.2026.113730_b42","series-title":"ICLR","article-title":"Dataset pruning: Reducing training data by examining generalization influence","author":"Yang","year":"2023"},{"key":"10.1016\/j.patcog.2026.113730_b43","article-title":"Data pruning via moving-one-sample-out","volume":"vol. 36","author":"Tan","year":"2024"},{"key":"10.1016\/j.patcog.2026.113730_b44","series-title":"ICML","first-page":"34533","article-title":"Provable data subset selection for efficient neural networks training","author":"Tukan","year":"2023"},{"key":"10.1016\/j.patcog.2026.113730_b45","series-title":"ICCV","first-page":"1004","article-title":"Reinforcement learning-guided data selection via redundancy assessment","author":"Yang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113730_b46","series-title":"ICML","article-title":"Efficient core-set selection for deep learning through squared loss minimization","author":"Chen","year":"2025"},{"key":"10.1016\/j.patcog.2026.113730_b47","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110392","article-title":"Embrace sustainable AI: dynamic data subset selection for image classification","volume":"151","author":"Yin","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113730_b48","series-title":"ICCV","first-page":"6869","article-title":"Class-proportional coreset selection for difficulty-separable data","author":"Tsai","year":"2025"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006953?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326006953?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T17:25:26Z","timestamp":1781112326000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326006953"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":48,"alternative-id":["S0031320326006953"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113730","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A unified analysis on cross-architecture generalizability of coresets","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113730","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"113730"}}