{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T14:47:15Z","timestamp":1774968435640,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T00:00:00Z","timestamp":1715558400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Foundation","doi-asserted-by":"publisher","award":["IIS-2406647,IIS-2406648"],"award-info":[{"award-number":["IIS-2406647,IIS-2406648"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,13]]},"DOI":"10.1145\/3589335.3641297","type":"proceedings-article","created":{"date-parts":[[2024,5,12]],"date-time":"2024-05-12T18:41:21Z","timestamp":1715539281000},"page":"1482-1485","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["DCAI: Data-centric Artificial Intelligence"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5054-954X","authenticated-orcid":false,"given":"Wei","family":"Jin","sequence":"first","affiliation":[{"name":"Emory University, Atlanta, GA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1826-4069","authenticated-orcid":false,"given":"Haohan","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Illinois Urbana-Champaign, Champaign, IL, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6677-7504","authenticated-orcid":false,"given":"Daochen","family":"Zha","sequence":"additional","affiliation":[{"name":"Rice University, Houston, TX, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8999-968X","authenticated-orcid":false,"given":"Qiaoyu","family":"Tan","sequence":"additional","affiliation":[{"name":"New York University Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4985-8724","authenticated-orcid":false,"given":"Yao","family":"Ma","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3479-4323","authenticated-orcid":false,"given":"Sharon","family":"Li","sequence":"additional","affiliation":[{"name":"University of Wisconsin Madison, Madison, WI, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5833-5215","authenticated-orcid":false,"given":"Su-In","family":"Lee","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,5,13]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Shayne Longpre, Nathan Lambert, Xinyi Wang, Niklas Muennighoff, Bairu Hou, Liangming Pan, Haewon Jeong, et al.","author":"Albalak Alon","year":"2024","unstructured":"Alon Albalak, Yanai Elazar, Sang Michael Xie, Shayne Longpre, Nathan Lambert, Xinyi Wang, Niklas Muennighoff, Bairu Hou, Liangming Pan, Haewon Jeong, et al. 2024. A Survey on Data Selection for Language Models. arXiv preprint arXiv:2402.16827 (2024)."},{"key":"e_1_3_2_1_2_1","volume-title":"The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=hESD2NJFg8","author":"Chen Zhikai","year":"2024","unstructured":"Zhikai Chen, Haitao Mao, Hongzhi Wen, Haoyu Han, Wei Jin, Haiyang Zhang, Hui Liu, and Jiliang Tang. 2024. Label-free Node Classification on Graphs with Large Language Models (LLMs). In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=hESD2NJFg8"},{"key":"e_1_3_2_1_3_1","unstructured":"Kristina Dachtler Michael Ortner Massimo Ferri Christof Eberst and Alexander Schiendorfer. [n. d.]. Data-centric and Goal-oriented AI for Robotic Repair Tasks. ( [n. d.])."},{"key":"e_1_3_2_1_4_1","volume-title":"A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation. arXiv preprint arXiv:2402.03358","author":"Hashemi Mohammad","year":"2024","unstructured":"Mohammad Hashemi, Shengbo Gong, Juntong Ni, Wenqi Fan, B Aditya Prakash, and Wei Jin. 2024. A Comprehensive Survey on Graph Reduction: Sparsification, Coarsening, and Condensation. arXiv preprint arXiv:2402.03358 (2024)."},{"key":"e_1_3_2_1_5_1","volume-title":"Data-centric artificial intelligence. arXiv preprint arXiv:2212.11854","author":"Jakubik Johannes","year":"2022","unstructured":"Johannes Jakubik, Michael V\u00f6ssing, Niklas K\u00fchl, Jannis Walk, and Gerhard Satzger. 2022. Data-centric artificial intelligence. arXiv preprint arXiv:2212.11854 (2022)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Wei Jin Yao Ma Xiaorui Liu Xianfeng Tang Suhang Wang and Jiliang Tang. 2020. Graph structure learning for robust graph neural networks. In KDD.","DOI":"10.1145\/3394486.3403049"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","unstructured":"Wei Jin Xianfeng Tang Haoming Jiang Zheng Li Danqing Zhang Jiliang Tang and Bing Yin. 2022. Condensing graphs via one-step gradient matching. In KDD.","DOI":"10.1145\/3534678.3539429"},{"key":"e_1_3_2_1_8_1","volume-title":"Teven Le Scao, Leandro Von Werra, Chenghao Mou, Eduardo Gonz\u00e1lez Ponferrada, Huu Nguyen, et al.","author":"Hugo Laurencc","year":"2022","unstructured":"Hugo Laurencc on, Lucile Saulnier, Thomas Wang, Christopher Akiki, Albert Villanova del Moral, Teven Le Scao, Leandro Von Werra, Chenghao Mou, Eduardo Gonz\u00e1lez Ponferrada, Huu Nguyen, et al. 2022. The bigscience roots corpus: A 1.6 tb composite multilingual dataset. In NeurIPS."},{"key":"e_1_3_2_1_9_1","volume-title":"2023 a. Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives. arXiv preprint arXiv:2307.16851","author":"Liu Haoyang","year":"2023","unstructured":"Haoyang Liu, Maheep Chaudhary, and Haohan Wang. 2023 a. Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives. arXiv preprint arXiv:2307.16851 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Energy-based out-of-distribution detection. Advances in neural information processing systems","author":"Liu Weitang","year":"2020","unstructured":"Weitang Liu, Xiaoyun Wang, John Owens, and Yixuan Li. 2020. Energy-based out-of-distribution detection. Advances in neural information processing systems , Vol. 33 (2020), 21464--21475."},{"key":"e_1_3_2_1_11_1","volume-title":"2023 b. FinGPT: Democratizing Internet-scale Data for Financial Large Language Models. arXiv preprint arXiv:2307.10485","author":"Liu Xiao-Yang","year":"2023","unstructured":"Xiao-Yang Liu, Guoxuan Wang, and Daochen Zha. 2023 b. FinGPT: Democratizing Internet-scale Data for Financial Large Language Models. arXiv preprint arXiv:2307.10485 (2023)."},{"key":"e_1_3_2_1_12_1","volume-title":"Zhaoran Wang, and Jian Guo. 2023 c. Dynamic Datasets and Market Environments for Financial Reinforcement Learning. arXiv preprint arXiv:2304.13174","author":"Liu Xiao-Yang","year":"2023","unstructured":"Xiao-Yang Liu, Ziyi Xia, Hongyang Yang, Jiechao Gao, Daochen Zha, Ming Zhu, Christina Dan Wang, Zhaoran Wang, and Jian Guo. 2023 c. Dynamic Datasets and Market Environments for Financial Reinforcement Learning. arXiv preprint arXiv:2304.13174 (2023)."},{"key":"e_1_3_2_1_13_1","volume-title":"Data Centric Artificial Intelligence: A Beginner's Guide","author":"Mahalle Parikshit N","unstructured":"Parikshit N Mahalle, Gitanjali R Shinde, Yashwant S Ingle, and Namrata N Wasatkar. 2023. Data-Centric AI in Mechanical Engineering. In Data Centric Artificial Intelligence: A Beginner's Guide. Springer, 97--108."},{"key":"e_1_3_2_1_14_1","volume-title":"International Conference on Machine Learning. PMLR","author":"Sun Yiyou","year":"2022","unstructured":"Yiyou Sun, Yifei Ming, Xiaojin Zhu, and Yixuan Li. 2022. Out-of-distribution detection with deep nearest neighbors. In International Conference on Machine Learning. PMLR, 20827--20840."},{"key":"e_1_3_2_1_15_1","volume-title":"Yong Jae Lee, and Eric P Xing","author":"Wang Haohan","year":"2022","unstructured":"Haohan Wang, Zeyi Huang, Hanlin Zhang, Yong Jae Lee, and Eric P Xing. 2022. Toward learning human-aligned cross-domain robust models by countering misaligned features. In Uncertainty in Artificial Intelligence. PMLR, 2075--2084."},{"key":"e_1_3_2_1_16_1","unstructured":"Cheng Yang Deyu Bo Jixi Liu Yufei Peng Boyu Chen Haoran Dai Ao Sun Yue Yu Yixin Xiao Qi Zhang et al. 2023. Data-centric Graph Learning: A Survey. arXiv preprint arXiv:2310.04987 (2023)."},{"key":"e_1_3_2_1_17_1","unstructured":"Daochen Zha Zaid Pervaiz Bhat Kwei-Herng Lai Fan Yang and Xia Hu. 2023 a. Data-centric AI: Perspectives and Challenges. In SDM."},{"key":"e_1_3_2_1_18_1","volume-title":"Kwei-Herng Lai, Fan Yang, Zhimeng Jiang, Shaochen Zhong, and Xia Hu.","author":"Zha Daochen","year":"2013","unstructured":"Daochen Zha, Zaid Pervaiz Bhat, Kwei-Herng Lai, Fan Yang, Zhimeng Jiang, Shaochen Zhong, and Xia Hu. 2013. Data-centric Artificial Intelligence: A Survey. arXiv preprint arXiv:2303.10158 (2013)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599553"},{"key":"e_1_3_2_1_20_1","volume-title":"Graph Data Augmentation for Graph Machine Learning: A Survey","author":"Zhao Tong","year":"2023","unstructured":"Tong Zhao, Wei Jin, Yozen Liu, Yingheng Wang, Gang Liu, Stephan G\u00fcnneman, Neil Shah, and Meng Jiang. 2023. Graph Data Augmentation for Graph Machine Learning: A Survey. IEEE Data Engineering Bulletin (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Alan Wee-Chung Liew, and Shirui Pan","author":"Zheng Xin","year":"2023","unstructured":"Xin Zheng, Yixin Liu, Zhifeng Bao, Meng Fang, Xia Hu, Alan Wee-Chung Liew, and Shirui Pan. 2023. Towards Data-centric Graph Machine Learning: Review and Outlook. arXiv preprint arXiv:2309.10979 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"OpenGSL: A Comprehensive Benchmark for Graph Structure Learning. arXiv preprint arXiv:2306.10280","author":"Zhou Zhiyao","year":"2023","unstructured":"Zhiyao Zhou, Sheng Zhou, Bochao Mao, Xuanyi Zhou, Jiawei Chen, Qiaoyu Tan, Daochen Zha, Can Wang, Yan Feng, and Chun Chen. 2023. OpenGSL: A Comprehensive Benchmark for Graph Structure Learning. arXiv preprint arXiv:2306.10280 (2023)."}],"event":{"name":"WWW '24: The ACM Web Conference 2024","location":"Singapore Singapore","acronym":"WWW '24","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2024"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3641297","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3589335.3641297","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:31:03Z","timestamp":1755822663000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3589335.3641297"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,13]]},"references-count":22,"alternative-id":["10.1145\/3589335.3641297","10.1145\/3589335"],"URL":"https:\/\/doi.org\/10.1145\/3589335.3641297","relation":{},"subject":[],"published":{"date-parts":[[2024,5,13]]},"assertion":[{"value":"2024-05-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}