{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:34:25Z","timestamp":1766129665345,"version":"3.48.0"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2023YFB3001900"],"award-info":[{"award-number":["2023YFB3001900"]}]},{"name":"Shenzhen Science and Technology Program","award":["KJZD20230923113901004"],"award-info":[{"award-number":["KJZD20230923113901004"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62572501"],"award-info":[{"award-number":["62572501"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Programs of Ningbo Municipal Natural Science Foundation","award":["2024J021"],"award-info":[{"award-number":["2024J021"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Serv. Comput."],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1109\/tsc.2025.3618908","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:38:48Z","timestamp":1759858728000},"page":"4349-4363","source":"Crossref","is-referenced-by-count":0,"title":["W2CB: Online Data Acquisition Optimization With Wasserstein Contextual Combinatorial Bandits"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4289-4431","authenticated-orcid":false,"given":"Yang","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2332-7941","authenticated-orcid":false,"given":"Xianzhi","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1518-002X","authenticated-orcid":false,"given":"Miao","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9433-7725","authenticated-orcid":false,"given":"Di","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1533-0865","authenticated-orcid":false,"given":"Yipeng","family":"Zhou","sequence":"additional","affiliation":[{"name":"Department of Computing, Faculty of Science and Engineering, Macquarie University, Sydney, NSW, Australia"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3451187"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2024.3486184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3491378"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3470320"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3482466"},{"key":"ref6","first-page":"17934","article-title":"Domain-wise data acquisition to improve performance under distribution shift","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"He"},{"key":"ref7","first-page":"118086","article-title":"Data acquisition via experimental design for data markets","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"article-title":"Data acquisition: A new frontier in data-centric AI","year":"2023","author":"Chen","key":"ref8"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2024.3495498"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2023.3242338"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.14778\/3685800.3685893"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00275"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3328526.3329589"},{"article-title":"AI training dataset market size, share & trends analysis report","year":"2024","author":"Research","key":"ref14"},{"article-title":"AWS data exchange","year":"2025","author":"Services","key":"ref15"},{"year":"2025","key":"ref16","article-title":"Databricks marketplace"},{"key":"ref17","first-page":"52033","article-title":"Rethinking data shapley for data selection tasks: Misleads and merits","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-71050-9"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.3160440402"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2695801"},{"key":"ref21","first-page":"21428","article-title":"Geometric dataset distances via optimal transport","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alvarez-Melis"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0566-z"},{"key":"ref23","first-page":"1","article-title":"Wasserstein embedding for graph learning","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Kolouri"},{"key":"ref24","first-page":"11492","article-title":"Neural contextual bandits with UCB-based exploration","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Zhou"},{"key":"ref25","first-page":"14203","article-title":"Combinatorial neural bandits","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Hwang"},{"key":"ref26","first-page":"2242","article-title":"Data shapley: Equitable valuation of data for machine learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Ghorbani"},{"key":"ref27","first-page":"1167","article-title":"Towards efficient data valuation based on the shapley value","volume-title":"Proc. 22nd Int. Conf. Artif. Intell. Statist.","author":"Jia"},{"key":"ref28","first-page":"1","article-title":"LAVA: Data valuation without pre-specified learning algorithms","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Just"},{"key":"ref29","first-page":"1","article-title":"Data valuation without training of a model","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ki"},{"key":"ref30","first-page":"24150","article-title":"DAVINZ: Data valuation using deep neural networks at initialization","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref31","first-page":"10837","article-title":"Validation Free and Replication Robust Volume-Based Data Valuation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref32","first-page":"10842","article-title":"Data valuation using reinforcement learning","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","author":"Yoon"},{"key":"ref33","first-page":"29915","article-title":"Optimizing Data Collection for Machine Learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mahmood"},{"key":"ref34","first-page":"61341","article-title":"Performance Scaling Via Optimal Transport: Enabling Data Selection From Partially Revealed Sources","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kang"},{"key":"ref35","first-page":"12491","article-title":"DsDm: Model-aware dataset selection with datamodels","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Engstrom"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref37","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1561\/9781680835519"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.568"},{"key":"ref40","first-page":"4933","article-title":"Can data diversity enhance learning generalization","volume-title":"Proc. 29th Int. Conf. Comput. Linguistics (COLING). Int. Committee Comput. Linguistics","author":"Yu"},{"key":"ref41","first-page":"8580","article-title":"Neural tangent kernel: Convergence and generalization in neural networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Jacot"},{"key":"ref42","first-page":"8570","article-title":"Wide neural networks of any depth evolve as linear models under gradient descent","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref43","first-page":"8139","article-title":"On exact computation with an infinitely wide neural net","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Arora"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.591"},{"key":"ref46","first-page":"649","article-title":"Character-Level Convolutional Networks for Text Classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref47","first-page":"1","article-title":"Pointer sentinel mixture models","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Merity"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","year":"2020","author":"Sanh","key":"ref50"},{"article-title":"OPT: Open pre-trained transformer language models","year":"2022","author":"Zhang","key":"ref51"},{"key":"ref52","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019","journal-title":"OpenAI"},{"key":"ref53","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref54","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-srw.37"},{"article-title":"AWS clean rooms differential privacy","year":"2024","author":"Services","key":"ref56"},{"article-title":"Differential privacy in snowflake data clean room","year":"2025","author":"Inc","key":"ref57"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/2770870"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3299869.3300078"},{"key":"ref60","first-page":"16483","article-title":"Strategic data sharing between competitors","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Tsoy"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE60146.2024.00275"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4727167"},{"key":"ref63","first-page":"669","article-title":"Selling data at an auction under privacy constraints","volume-title":"Proc. 36th Conf. Uncertainty Artif. Intell.","author":"Zhang"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3391403.3399500"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.14778\/3342263.3342637"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-12423-5_14"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3472291"},{"key":"ref68","first-page":"151","article-title":"Combinatorial multi-armed bandit: General framework and applications","volume-title":"Proc. 30th Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref69","first-page":"586","article-title":"Parametric bandits: The generalized linear case","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Filippi"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00149"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/871"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00653"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_45"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106796"},{"article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","year":"2018","author":"Warden","key":"ref75"},{"article-title":"Hello edge: Keyword spotting on microcontrollers","year":"2017","author":"Zhang","key":"ref76"},{"key":"ref77","first-page":"487","article-title":"Exploiting generative models in discriminative classifiers","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Jaakkola"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_11"},{"key":"ref79","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"key":"ref80","first-page":"1177","article-title":"Random features for large-scale kernel machines","volume-title":"Proc. 21st Annu. Conf. Neural Inf. Process. Syst.","author":"Rahimi"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/BF01588971"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6377(03)00062-2"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref84","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref85","first-page":"4716","article-title":"Efficient data subset selection to generalize training across models: Transductive and inductive networks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Jain"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.766"}],"container-title":["IEEE Transactions on Services Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4629386\/11298270\/11195778.pdf?arnumber=11195778","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T07:30:26Z","timestamp":1766129426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195778\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":86,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tsc.2025.3618908","relation":{},"ISSN":["1939-1374","2372-0204"],"issn-type":[{"type":"electronic","value":"1939-1374"},{"type":"electronic","value":"2372-0204"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}