{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T09:53:38Z","timestamp":1773482018674,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":24,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,6,9]]},"DOI":"10.1145\/3650203.3663329","type":"proceedings-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T20:13:23Z","timestamp":1717013603000},"page":"23-28","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["AIDB: a Sparsely Materialized Database for Queries using Machine Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-0353-4184","authenticated-orcid":false,"given":"Tengjun","family":"Jin","sequence":"first","affiliation":[{"name":"UIUC"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9041-8376","authenticated-orcid":false,"given":"Akash","family":"Mittal","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9860-6325","authenticated-orcid":false,"given":"Chenghao","family":"Mo","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0202-0597","authenticated-orcid":false,"given":"Jiahao","family":"Fang","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2120-1879","authenticated-orcid":false,"given":"Chengsong","family":"Zhang","sequence":"additional","affiliation":[{"name":"UIUC"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9074-2037","authenticated-orcid":false,"given":"Timothy","family":"Dai","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9860-9938","authenticated-orcid":false,"given":"Daniel","family":"Kang","sequence":"additional","affiliation":[{"name":"UIUC"}]}],"member":"320","published-online":{"date-parts":[[2024,6,9]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2019.00132"},{"key":"e_1_3_2_1_2_1","volume-title":"Predicate Optimization for a Visual Analytics Database. ICDE","author":"Anderson Michael R","year":"2019","unstructured":"Michael R Anderson, Michael Cafarella, Thomas F Wenisch, and German Ros. 2019. Predicate Optimization for a Visual Analytics Database. ICDE (2019)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.14778\/3598581.3598599"},{"key":"e_1_3_2_1_4_1","volume-title":"OTIF: Efficient Tracker Pre-processing over Large Video Datasets.","author":"Bastani Favyen","year":"2022","unstructured":"Favyen Bastani and Samuel Madden. 2022. OTIF: Efficient Tracker Pre-processing over Large Video Datasets. (2022)."},{"key":"e_1_3_2_1_5_1","volume-title":"Yaml ain't markup language (yaml\u2122) version 1.1. Working Draft 2008 5","author":"Ben-Kiki Oren","year":"2009","unstructured":"Oren Ben-Kiki, Clark Evans, and Brian Ingerson. 2009. Yaml ain't markup language (yaml\u2122) version 1.1. Working Draft 2008 5 (2009), 11."},{"key":"e_1_3_2_1_6_1","unstructured":"Marshall Carter and Sujoy Dutta. 2022. Parallel ML: How Compass Built a Framework for Training Many Machine Learning Models on Databricks. https:\/\/www.databricks.com\/blog\/2022\/07\/20\/parallel-ml-how-compass-built-a-framework-for-training-many-machine-learning-models-on-databricks.html"},{"key":"e_1_3_2_1_7_1","volume-title":"Alemi","author":"Clement Colin B.","year":"2019","unstructured":"Colin B. Clement, Matthew Bierbaum, Kevin P. O'Keeffe, and Alexander A. Alemi. 2019. On the Use of ArXiv as a Dataset. arXiv:1905.00075 [cs.IR]"},{"key":"e_1_3_2_1_8_1","unstructured":"Jonathan Falvey. 2023. ChatGPT Tweets. https:\/\/huggingface.co\/datasets\/deberain\/ChatGPT-Tweets"},{"key":"e_1_3_2_1_9_1","unstructured":"Google. 2023. Pricing | Cloud Natural Language. https:\/\/cloud.google.com\/natural-language\/pricing"},{"key":"e_1_3_2_1_10_1","unstructured":"Google. 2023. Pricing | Cloud Vision API. https:\/\/cloud.google.com\/vision\/pricing"},{"key":"e_1_3_2_1_11_1","volume-title":"DeepEverest: accelerating declarative top-K queries for deep neural network interpretation. arXiv preprint arXiv:2104.02234","author":"He Dong","year":"2021","unstructured":"Dong He, Maureen Daum, Walter Cai, and Magdalena Balazinska. 2021. DeepEverest: accelerating declarative top-K queries for deep neural network interpretation. arXiv preprint arXiv:2104.02234 (2021)."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3318464.3389766"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.14778\/3611540.3611581"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.14778\/3372716.3372725"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_3_2_1_16_1","volume-title":"Approximate Selection with Guarantees using Proxies. PVLDB","author":"Kang Daniel","year":"2020","unstructured":"Daniel Kang, Edward Gan, Peter Bailis, Tatsunori Hashimoto, and Matei Zaharia. 2020. Approximate Selection with Guarantees using Proxies. PVLDB (2020)."},{"key":"e_1_3_2_1_17_1","volume-title":"Accelerating Approximate Aggregation Queries with Expensive Predicates. PVLDB","author":"Kang Daniel","year":"2021","unstructured":"Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, Yi Sun, and Matei Zaharia. 2021. Accelerating Approximate Aggregation Queries with Expensive Predicates. PVLDB (2021)."},{"key":"e_1_3_2_1_18_1","volume-title":"Semantic Indexes for Machine Learning-based Queries over Unstructured Data. SIGMOD","author":"Kang Daniel","year":"2022","unstructured":"Daniel Kang, John Guibas, Peter Bailis, Tatsunori Hashimoto, and Matei Zaharia. 2022. Semantic Indexes for Machine Learning-based Queries over Unstructured Data. SIGMOD (2022)."},{"key":"e_1_3_2_1_19_1","volume-title":"Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics. PVLDB","author":"Kang Daniel","year":"2021","unstructured":"Daniel Kang, Ankit Mathur, Teja Veeramacheneni, Peter Bailis, and Matei Zaharia. 2021. Jointly Optimizing Preprocessing and Inference for DNN-based Visual Analytics. PVLDB (2021)."},{"key":"e_1_3_2_1_20_1","unstructured":"Leslie Kish. 1965. Survey sampling. Number 04; HN29 K5."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Yao Lu Aakanksha Chowdhery Srikanth Kandula and Surajit Chaudhuri. 2018. Accelerating Machine Learning Inference with Probabilistic Predicates. In SIGMOD. ACM 1493--1508.","DOI":"10.1145\/3183713.3183751"},{"key":"e_1_3_2_1_22_1","unstructured":"MindsDB. [n.d.]. Machine Learning in Your Database Using SQL. https:\/\/mindsdb.com\/"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3514221.3526142"},{"key":"e_1_3_2_1_24_1","first-page":"10","article-title":"Spark: Cluster computing with working sets","volume":"10","author":"Zaharia Matei","year":"2010","unstructured":"Matei Zaharia, Mosharaf Chowdhury, Michael J Franklin, Scott Shenker, and Ion Stoica. 2010. Spark: Cluster computing with working sets. HotCloud 10, 10--10 (2010), 95.","journal-title":"HotCloud"}],"event":{"name":"SIGMOD\/PODS '24: International Conference on Management of Data","location":"Santiago AA Chile","acronym":"SIGMOD\/PODS '24","sponsor":["SIGMOD ACM Special Interest Group on Management of Data"]},"container-title":["Proceedings of the Eighth Workshop on Data Management for End-to-End Machine Learning"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650203.3663329","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3650203.3663329","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:03:31Z","timestamp":1750291411000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3650203.3663329"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,9]]},"references-count":24,"alternative-id":["10.1145\/3650203.3663329","10.1145\/3650203"],"URL":"https:\/\/doi.org\/10.1145\/3650203.3663329","relation":{},"subject":[],"published":{"date-parts":[[2024,6,9]]},"assertion":[{"value":"2024-06-09","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}