{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T10:56:34Z","timestamp":1777460194612,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"name":"National Recovery and Resilience Plan Greece 2.0 (European Union \u2013 NextGenerationEU)","award":["MIS 5154714"],"award-info":[{"award-number":["MIS 5154714"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,27]]},"DOI":"10.1145\/3805621.3807646","type":"proceedings-article","created":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:08:45Z","timestamp":1777381725000},"page":"346-354","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Block-Aware Distributed Data Pipelines for Out-of-Core Tabular Machine Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-4452-891X","authenticated-orcid":false,"given":"Dimitris","family":"Metaxakis","sequence":"first","affiliation":[{"name":"Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Archimedes Unit, Athena Research Center, Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5282-8064","authenticated-orcid":false,"given":"Argiris","family":"Sofotasios","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Archimedes Unit, Athena Research Center, Athens, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2888-6515","authenticated-orcid":false,"given":"Chrysostomos","family":"Stylios","sequence":"additional","affiliation":[{"name":"Industrial Systems Institute, Athena Research Center, Patras, Greece and Department of Informatics and Telecommunications, University of Ioannina, Arta, Greece"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2528-7568","authenticated-orcid":false,"given":"Panagiotis","family":"Hadjidoukas","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering and Informatics, University of Patras, Patras, Greece and Industrial Systems Institute, Athena Research Center, Patras, Greece"}]}],"member":"320","published-online":{"date-parts":[[2026,4,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517337"},{"key":"e_1_3_2_1_2_1","volume-title":"Understanding the Python GIL. Retrieved","year":"2026","unstructured":"Beazley, David. 2010. Understanding the Python GIL. Retrieved April 6, 2026 from https:\/\/www.dabeaz.com\/python\/UnderstandingGIL.pdf Presented at PyCON 2010, Atlanta, Georgia."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation","author":"Berger Emery D.","year":"2023","unstructured":"Emery D. Berger, Sam Stern, and Juan Altmayer Pizzorno. 2023. Triangulating Python Performance Issues with SCALENE. In Proceedings of the 17th USENIX Symposium on Operating Systems Design and Implementation (Boston, MA, USA) (OSDI '23). USENIX Association, USA, 51\u201364."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-023-00862-w"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CCGrid51090.2021.00018"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3149371"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS '21","volume":"1447","author":"Gorishniy Yury","year":"2021","unstructured":"Yury Gorishniy, Ivan Rubachev, Valentin Khrulkov, and Artem Babenko. 2021. Revisiting deep learning models for tabular data. In Proceedings of the 35th International Conference on Neural Information Processing Systems (NeurIPS '21, Vol. 34). Curran Associates Inc., Red Hook, NY, USA, Article 1447, 12 pages."},{"key":"e_1_3_2_1_8_1","volume-title":"Proceedings of the 2022 USENIX Annual Technical Conference (Carlsbad, CA, USA) (USENIX ATC '22). USENIX Association, USA, 689\u2013706","author":"Graur Dan","year":"2022","unstructured":"Dan Graur, Damien Aymon, Dan Kluser, Tanguy Albrici, Chandramohan A. Thekkath, and Ana Klimovic. 2022. Cachew: Machine Learning Input Data Processing as a Service. In Proceedings of the 2022 USENIX Annual Technical Conference (Carlsbad, CA, USA) (USENIX ATC '22). USENIX Association, USA, 689\u2013706."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC '24). USENIX Association, USA, Article 40","author":"Graur Dan","year":"2024","unstructured":"Dan Graur, Oto Mraz, Muyu Li, Sepehr Pourghannad, Chandramohan A. Thekkath, and Ana Klimovic. 2024. Pecan: cost-efficient ML data preprocessing with automatic transformation ordering and hybrid placement. In Proceedings of the 2024 USENIX Conference on Usenix Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC '24). USENIX Association, USA, Article 40, 17 pages."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2020.100517"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the 2nd MLSys Conference","volume":"1","author":"Hashemi Sayed Hadi","year":"2019","unstructured":"Sayed Hadi Hashemi, Sangeetha Abdu Jyothi, and Roy Campbell. 2019. TicTac: Accelerating Distributed Deep Learning with Communication Scheduling. In Proceedings of the 2nd MLSys Conference (Palo Alto, CA, USA), Vol. 1. MLSys, USA, 418\u2013430."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","volume":"10","author":"Huang Yanping","year":"2019","unstructured":"Yanping Huang, Youlong Cheng, Ankur Bapna, Orhan Firat, Mia Xu Chen, Dehao Chen, HyoukJoong Lee, Jiquan Ngiam, Quoc V. Le, Yonghui Wu, and Zhifeng Chen. 2019. GPipe: efficient training of giant neural networks using pipeline parallelism. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (Vancouver, Canada) (NeurIPS '19, Vol. 32). Curran Associates, Inc., Red Hook, NY, USA, Article 10, 10 pages."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 2nd MLSys Conference","volume":"1","author":"Jayarajan Anand","year":"2019","unstructured":"Anand Jayarajan, Jinliang Wei, Garth Gibson, Alexandra Fedorova, and Gennady Pekhimenko. 2019. Priority-based Parameter Propagation for Distributed DNN Training. In Proceedings of the 2nd MLSys Conference (Palo Alto, CA, USA), Vol. 1. MLSys, USA, 132\u2013145."},{"key":"e_1_3_2_1_14_1","unstructured":"Alex Krizhevsky. 2014. One weird trick for parallelizing convolutional neural networks. arXiv:1404.5997 https:\/\/arxiv.org\/abs\/1404.5997"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 18th USENIX Conference on File and Storage Technologies","author":"Kumar Abhishek Vijaya","year":"2020","unstructured":"Abhishek Vijaya Kumar and Muthian Sivathanu. 2020. Quiver: An Informed Storage Cache for Deep Learning. In Proceedings of the 18th USENIX Conference on File and Storage Technologies (Santa Clara, CA, USA) (FAST '20). USENIX Association, USA, 283\u2013296."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.14778\/3446095.3446100"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.111225"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476374"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3642970.3655824"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","unstructured":"Rahma Nouaji Stella Bitchebe Ricardo Macedo and Oana Balmau. 2025. MinatoLoader: Accelerating Machine Learning Training Through Efficient Data Preprocessing. arXiv:2509.10712 https:\/\/arxiv.org\/abs\/2509 10712","DOI":"10.1145\/3767295.3769376"},{"issue":"0","key":"e_1_3_2_1_22_1","first-page":"0","article-title":"DALI (Data Loading Library): A GPU-accelerated library for data loading and pre-processing to accelerate deep learning applications","volume":"2","author":"Development Team NVIDIA","year":"2026","unstructured":"NVIDIA Development Team. 2026. DALI (Data Loading Library): A GPU-accelerated library for data loading and pre-processing to accelerate deep learning applications, Version 2.0.0. Retrieved April 6, 2026 from https:\/\/github.com\/nvidia\/dali","journal-title":"Version"},{"key":"e_1_3_2_1_23_1","volume-title":"FHV Trip Record Data. Retrieved","author":"NYC Taxi and Limousine Commission","year":"2026","unstructured":"NYC Taxi and Limousine Commission. 2026. FHV Trip Record Data. Retrieved April 6, 2026 from https:\/\/www.nyc.gov\/site\/tlc\/about\/tlc-trip-record-data.page"},{"key":"e_1_3_2_1_24_1","volume-title":"Proceedings of the 1st International Workshop on Industrial Recommendation Systems (IRS '20)","author":"Oldridge Even","year":"2020","unstructured":"Even Oldridge, Julio Perez, Ben Frederickson, Minseok Lee, Zehuan Wang, Lei Wu, Fan Yu, Rick Zamora, Onur Yilmaz, Alec Gunny, Nicolas Koumchatzky, and Vinh Nguyen. 2020. Merlin: A GPU Accelerated Recommendation Framework. In Proceedings of the 1st International Workshop on Industrial Recommendation Systems (IRS '20)."},{"key":"e_1_3_2_1_25_1","volume-title":"Proceedings of the 33rd International Conference on Neural Information Processing Systems","volume":"721","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. PyTorch: An Imperative Style, High-Performance Deep Learning Library. In Proceedings of the 33rd International Conference on Neural Information Processing Systems (Vancouver, Canada) (NeurIPS '19, Vol. 32). Curran Associates, Inc., Red Hook, NY, USA, Article 721, 12 pages."},{"key":"e_1_3_2_1_26_1","first-page":"39","article-title":"Polars: Extremely fast Query Engine for DataFrames, written in Rust","volume":"1","author":"Team Polars Development","year":"2026","unstructured":"Polars Development Team. 2026. Polars: Extremely fast Query Engine for DataFrames, written in Rust, Version 1.39.3. Retrieved April 6, 2026 from https:\/\/github.com\/pola-rs\/polars","journal-title":"Version"},{"key":"e_1_3_2_1_27_1","volume-title":"Horovod: Fast and Easy Distributed Deep Learning in TensorFlow. arXiv:1802.05799 https:\/\/arxiv.org\/abs\/1802.05799","author":"Sergeev Alexander","year":"2018","unstructured":"Alexander Sergeev and Mike Del Balso. 2018. Horovod: Fast and Easy Distributed Deep Learning in TensorFlow. arXiv:1802.05799 https:\/\/arxiv.org\/abs\/1802.05799"},{"key":"e_1_3_2_1_28_1","unstructured":"Mohammad Shoeybi Mostofa Patwary Raul Puri Patrick LeGresley Jared Casper and Bryan Catanzaro. 2019. Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism. arXiv:1909.08053 https:\/\/arxiv.org\/abs\/1909.08053"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-7692811\/v1"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627703.3629578"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377454"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10766-022-00741-6"},{"issue":"0","key":"e_1_3_2_1_33_1","first-page":"0","article-title":"Theine: High performance in-memory cache inspired by Caffeine","volume":"2","author":"J.","year":"2025","unstructured":"Yiling-J. 2025. Theine: High performance in-memory cache inspired by Caffeine, Version 2.0.0. Retrieved April 6, 2026 from https:\/\/github.com\/Yiling-J\/theine","journal-title":"Version"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 2017 USENIX Conference Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC '17). USENIX Association, USA, 181\u2013193","author":"Zhang Hao","unstructured":"Hao Zhang, Zeyu Zheng, Shizhen Xu, Wei Dai, Qirong Ho, Xiaodan Liang, Zhiting Hu, Jinliang Wei, Pengtao Xie, and Eric P. Xing. 2017. Poseidon: an efficient communication architecture for distributed deep learning on GPU clusters. In Proceedings of the 2017 USENIX Conference Annual Technical Conference (Santa Clara, CA, USA) (USENIX ATC '17). USENIX Association, USA, 181\u2013193."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.14778\/3705829.3705861"}],"event":{"name":"EuroSys '26: 21st European Conference on Computer Systems","location":"Edinburgh Scotland Uk","acronym":"EuroMLSys '26","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Sixth European Workshop on Machine Learning and Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3805621.3807646","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,28]],"date-time":"2026-04-28T13:11:44Z","timestamp":1777381904000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3805621.3807646"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,27]]},"references-count":35,"alternative-id":["10.1145\/3805621.3807646","10.1145\/3805621"],"URL":"https:\/\/doi.org\/10.1145\/3805621.3807646","relation":{},"subject":[],"published":{"date-parts":[[2026,4,27]]},"assertion":[{"value":"2026-04-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}