{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T01:03:18Z","timestamp":1782867798355,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":33,"publisher":"ACM","funder":[{"DOI":"10.13039\/100018694","name":"HORIZON EUROPE Marie Sklodowska-Curie Actions","doi-asserted-by":"publisher","award":["101072456"],"award-info":[{"award-number":["101072456"]}],"id":[{"id":"10.13039\/100018694","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,11,10]]},"DOI":"10.1145\/3746252.3761305","type":"proceedings-article","created":{"date-parts":[[2025,11,8]],"date-time":"2025-11-08T01:03:42Z","timestamp":1762563822000},"page":"1958-1967","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Chunked Data Shapley: A Scalable Dataset Quality Assessment for Machine Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-3958-6934","authenticated-orcid":false,"given":"Andreas","family":"Loizou","sequence":"first","affiliation":[{"name":"Database and Knowledge Systems Lab, School of ECE, National Technical University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4420-8949","authenticated-orcid":false,"given":"Dimitrios","family":"Tsoumakos","sequence":"additional","affiliation":[{"name":"Database and Knowledge Systems Lab, School of ECE, National Technical University of Athens, Athens, Greece"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,11,10]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Handbook of Neural Computation","author":"Almeida Luis B","unstructured":"Luis B Almeida. 2020. Multilayer perceptrons. In Handbook of Neural Computation. CRC Press, C1-2."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/0925-2312(93)90006-O"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3592031"},{"key":"e_1_3_2_1_4_1","volume-title":"Methodologies for data quality assessment and improvement. ACM computing surveys (CSUR)","author":"Batini Carlo","year":"2009","unstructured":"Carlo Batini, Cinzia Cappiello, Chiara Francalanci, and Andrea Maurino. 2009. Methodologies for data quality assessment and improvement. ACM computing surveys (CSUR), Vol. 41, 3 (2009), 1-52."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.24432\/C5XW20"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/342009.335388"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","unstructured":"Song Chen. 2017. Beijing Multi-Site Air Quality. UCI Machine Learning Repository. DOI: https:\/\/doi.org\/10.24432\/C5RK5G.","DOI":"10.24432\/C5RK5G"},{"key":"e_1_3_2_1_8_1","volume-title":"On the complexity of cooperative solution concepts. Mathematics of operations research","author":"Deng Xiaotie","year":"1994","unstructured":"Xiaotie Deng and Christos H Papadimitriou. 1994. On the complexity of cooperative solution concepts. Mathematics of operations research, Vol. 19, 2 (1994), 257-266."},{"key":"e_1_3_2_1_9_1","unstructured":"Amirata Ghorbani Michael P. Kim and James Zou. 2020. A Distributional Framework for Data Valuation. arXiv:2002.12334 [cs.LG] https:\/\/arxiv.org\/abs\/2002.12334"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 2242-2251","author":"Ghorbani Amirata","year":"2019","unstructured":"Amirata Ghorbani and James Zou. 2019. Data shapley: Equitable valuation of data for machine learning. In International conference on machine learning. PMLR, 2242-2251."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271731"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijpe.2014.04.018"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.24432\/C58K54"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12599-024-00857-8"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1093\/jamia\/ocx084"},{"key":"e_1_3_2_1_16_1","volume-title":"International Conference on Machine Learning. PMLR, 21730-21755","author":"Liu Zhihong","year":"2023","unstructured":"Zhihong Liu, Hoang Anh Just, Xiangyu Chang, Xi Chen, and Ruoxi Jia. 2023. 2d-shapley: A framework for fragmented data valuation. In International Conference on Machine Learning. PMLR, 21730-21755."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3701717.3733227"},{"key":"e_1_3_2_1_18_1","first-page":"237","volume-title":"Proceedings of the 36th International Conference on Database and Expert Systems Applications (DEXA","author":"Loizou Andreas","year":"2025","unstructured":"Andreas Loizou and Dimitrios Tsoumakos. 2025. Analytics Modelling over Multiple Datasets Using Vector Embeddings. In Proceedings of the 36th International Conference on Database and Expert Systems Applications (DEXA 2025). Springer, 237-253."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681367"},{"key":"e_1_3_2_1_20_1","first-page":"1","article-title":"Sampling permutations for shapley value estimation","volume":"23","author":"Mitchell Rory","year":"2022","unstructured":"Rory Mitchell, Joshua Cooper, Eibe Frank, and Geoffrey Holmes. 2022. Sampling permutations for shapley value estimation. Journal of Machine Learning Research, Vol. 23, 43 (2022), 1-46.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2025.102549"},{"key":"e_1_3_2_1_22_1","volume-title":"International Conference on Extending Database Technology (EDBT).","author":"Mohammed Sedir","year":"2025","unstructured":"Sedir Mohammed, Felix Naumann, and Hazar Harmouch. 2025b. Step-by-Step Data Cleaning Recommendations to Improve ML Prediction Accuracy. In International Conference on Extending Database Technology (EDBT)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","unstructured":"S. Moro P. Rita and P. Cortez. 2014. Bank Marketing. UCI Machine Learning Repository. DOI: https:\/\/doi.org\/10.24432\/C5K306.","DOI":"10.24432\/C5K306"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404193"},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 11th WSEAS International Conference on Sustainability in Science Engineering. 28-31","author":"Popescu MARIUS-CONSTANTIN","year":"2009","unstructured":"MARIUS-CONSTANTIN Popescu, VALENTINA Balas, ONISIFOR Olaru, and NIKOS Mastorakis. 2009. The backpropagation algorithm functions for the multilayer perceptron. In Proceedings of the 11th WSEAS International Conference on Sustainability in Science Engineering. 28-31."},{"key":"e_1_3_2_1_26_1","volume-title":"The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review","author":"Rosenblatt Frank","year":"1958","unstructured":"Frank Rosenblatt. 1958. The perceptron: a probabilistic model for information storage and organization in the brain. Psychological review, Vol. 65, 6 (1958), 386."},{"key":"e_1_3_2_1_27_1","volume-title":"The Shapley value: essays in honor of Lloyd S. Shapley","author":"Roth Alvin E","unstructured":"Alvin E Roth. 1988. The Shapley value: essays in honor of Lloyd S. Shapley. Cambridge University Press."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"crossref","unstructured":"Lloyd S Shapley et al. 1953. A value for n-person games. (1953).","DOI":"10.1515\/9781400881970-018"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/make7010006"},{"key":"e_1_3_2_1_30_1","volume-title":"Data shapley in one training run. arXiv preprint arXiv:2406.11011","author":"Wang Jiachen T","year":"2024","unstructured":"Jiachen T Wang, Prateek Mittal, Dawn Song, and Ruoxi Jia. 2024a. Data shapley in one training run. arXiv preprint arXiv:2406.11011 (2024)."},{"key":"e_1_3_2_1_31_1","unstructured":"Jiachen T. Wang Tianji Yang James Zou Yongchan Kwon and Ruoxi Jia. 2024b. Rethinking Data Shapley for Data Selection Tasks: Misleads and Merits. arXiv:2405.03875 [cs.LG] https:\/\/arxiv.org\/abs\/2405.03875"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1080\/07421222.1996.11518099"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711118"}],"event":{"name":"CIKM '25: The 34th ACM International Conference on Information and Knowledge Management","location":"Seoul Republic of Korea","acronym":"CIKM '25","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the 34th ACM International Conference on Information and Knowledge Management"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746252.3761305","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T01:17:10Z","timestamp":1765502230000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746252.3761305"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,10]]},"references-count":33,"alternative-id":["10.1145\/3746252.3761305","10.1145\/3746252"],"URL":"https:\/\/doi.org\/10.1145\/3746252.3761305","relation":{},"subject":[],"published":{"date-parts":[[2025,11,10]]},"assertion":[{"value":"2025-11-10","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}