{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T08:28:50Z","timestamp":1768033730748,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":72,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,30]],"date-time":"2025-03-30T00:00:00Z","timestamp":1743292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,30]]},"DOI":"10.1145\/3689031.3696100","type":"proceedings-article","created":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:25:20Z","timestamp":1742970320000},"page":"345-359","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Moko: Marrying Python with Big Data Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3629-7892","authenticated-orcid":false,"given":"Ke","family":"Meng","sequence":"first","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7687-7342","authenticated-orcid":false,"given":"Tao","family":"He","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4650-7352","authenticated-orcid":false,"given":"Sijie","family":"Shen","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7535-452X","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5641-2452","authenticated-orcid":false,"given":"Wenyuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6851-1366","authenticated-orcid":false,"given":"Jingren","family":"Zhou","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"[n.d.]. Production-Grade Container Orchestration. https:\/\/kubernetes.io."},{"key":"e_1_3_2_1_2_1","volume-title":"12th USENIX symposium on operating systems design and implementation (OSDI 16)","author":"Abadi Mart\u00edn","year":"2016","unstructured":"Mart\u00edn Abadi, Paul Barham, Jianmin Chen, Zhifeng Chen, Andy Davis, Jeffrey Dean, Matthieu Devin, Sanjay Ghemawat, Geoffrey Irving, Michael Isard, et al. 2016. Tensorflow: A system for large-scale machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16). 265--283."},{"key":"e_1_3_2_1_3_1","unstructured":"Param Aggarwal. 2018. fashion-product-images-dataset. https:\/\/www.kaggle.com\/datasets\/paramaggarwal\/fashion-product-images-dataset."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.14778\/3236187.3236195"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2019.00088"},{"key":"e_1_3_2_1_6_1","volume-title":"Amazon Web Service","author":"Inc.","year":"2022","unstructured":"Inc. Amazon Web Service. 2022. Amazon Simple Storage Service: Object Storage built to retrieve any amount of data from anywhere. https:\/\/aws.amazon.com\/s3\/."},{"key":"e_1_3_2_1_7_1","unstructured":"Renzo Angles J\u00e1nos Benjamin Antal Alex Averbuch Peter A. Boncz Orri Erling Andrey Gubichev Vlad Haprian Moritz Kaufmann Josep-Llu\u00eds Larriba-Pey Norbert Mart\u00ednez-Bazan J\u00f3zsef Marton Marcus Paradies Minh-Duc Pham Arnau Prat-P\u00e9rez Mirko Spasic Benjamin A. Steer G\u00e1bor Sz\u00e1rnyas and Jack Waudby. 2020. The LDBC Social Network Benchmark. CoRR abs\/2001.02299 (2020). arXiv:2001.02299 http:\/\/arxiv.org\/abs\/2001.02299"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/1391956.1391959"},{"key":"e_1_3_2_1_9_1","volume-title":"Cython: C-Extensions for Python. https:\/\/cython.org\/.","author":"Cython","year":"2023","unstructured":"Cython author. 2023. Cython: C-Extensions for Python. https:\/\/cython.org\/."},{"key":"e_1_3_2_1_10_1","unstructured":"Mojo author. 2023. Mojo: the programming language for all AI developers. https:\/\/www.modular.com\/mojo."},{"key":"e_1_3_2_1_11_1","volume-title":"Numba: A High Performance Python Compiler. https:\/\/numba.pydata.org\/.","author":"Numba","year":"2023","unstructured":"Numba authors. 2023. Numba: A High Performance Python Compiler. https:\/\/numba.pydata.org\/."},{"key":"e_1_3_2_1_12_1","volume-title":"Pandas: Python Data Analysis Library. https:\/\/pandas.pydata.org\/.","author":"Pandas","year":"2022","unstructured":"Pandas authors. 2022. Pandas: Python Data Analysis Library. https:\/\/pandas.pydata.org\/."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150412"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1155\/2013\/702694"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the 7th International Workshop on Languages and Compilers for Parallel Computing (LCPC '94)","author":"Blume William","year":"1994","unstructured":"William Blume, Rudolf Eigenmann, Keith Faigin, John Grout, Jay Hoeflinger, David A. Padua, Paul Petersen, William M. Pottenger, Lawrence Rauchwerger, Peng Tu, and Stephen Weatherford. 1994. Polaris: Improving the Effectiveness of Parallelizing Compilers. In Proceedings of the 7th International Workshop on Languages and Compilers for Parallel Computing (LCPC '94). Springer-Verlag, Berlin, Heidelberg, 141--154."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2018.06.032"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CGO51591.2021.9370332"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824077"},{"key":"e_1_3_2_1_19_1","unstructured":"Inc. ClickHouse. 2022. ClickHouse: Fast Open-Source OLAP DBMS. https:\/\/clickhouse.com\/."},{"key":"e_1_3_2_1_20_1","unstructured":"The Transaction Processing Performance Council. 2023. TPCH benchmark. https:\/\/www.tpc.org\/tpch\/."},{"key":"e_1_3_2_1_21_1","unstructured":"Vinicius Couto Luciano Zago Herv\u00e9 Yviquel and Guido Ara\u00fajo. 2022. Source Matching and Rewriting. arXiv:2202.04153 [cs.PL]"},{"key":"e_1_3_2_1_22_1","volume-title":"SuiteSparse:GraphBLAS: Graph Algorithms in the Language of Sparse Linear Algebra. ACM Trans. Math. Softw. ((under revision)","author":"Davis Timothy A.","year":"2022","unstructured":"Timothy A. Davis. 2022. Algorithm 10xx: SuiteSparse:GraphBLAS: Graph Algorithms in the Language of Sparse Linear Algebra. ACM Trans. Math. Softw. ((under revision) 2022). See GraphBLAS\/Doc\/-toms_parallel_grb2.pdf."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/1327452.1327492"},{"key":"e_1_3_2_1_24_1","unstructured":"Dask developers. 2023. dask: Scale the Python tools you love. https:\/\/www.dask.org."},{"key":"e_1_3_2_1_25_1","unstructured":"Koalas developers. 2023. Koalas: pandas API on Apache Spark. https:\/\/koalas.readthedocs.io\/."},{"key":"e_1_3_2_1_26_1","unstructured":"NumPy developers. 2022. NumPy: The fundamental package for scientific computing with Python. https:\/\/www.numpy.org\/."},{"key":"e_1_3_2_1_27_1","unstructured":"NetworkX developers. 2023. NetworkX: Network Analysis in Python. https:\/\/networkx.org\/."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/3476311.3476369"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3282488"},{"key":"e_1_3_2_1_30_1","volume-title":"Arrow: A cross-language development platform for in-memory analytics. https:\/\/github.com\/apache\/arrow.","author":"Software Foundation The Apache","year":"2022","unstructured":"The Apache Software Foundation. 2022. Arrow: A cross-language development platform for in-memory analytics. https:\/\/github.com\/apache\/arrow."},{"key":"e_1_3_2_1_31_1","unstructured":"The Presto Foundation. 2023. presto: Fast and Reliable SQL Engine for Data Analytics and the Open Lakehouse. https:\/\/prestodb.io\/."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CLOUD.2016.0034"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3377555.3377893"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3296957.3173182"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173182"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/2741948.2741968"},{"key":"e_1_3_2_1_37_1","first-page":"2","article-title":"PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs","volume":"12","author":"Gonzalez Joseph E","year":"2012","unstructured":"Joseph E Gonzalez, Yucheng Low, Haijie Gu, Danny Bickson, and Carlos Guestrin. 2012. PowerGraph: Distributed Graph-Parallel Computation on Natural Graphs.. In OSDI, Vol. 12. 2.","journal-title":"OSDI"},{"key":"e_1_3_2_1_38_1","volume-title":"11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14)","author":"Gonzalez Joseph E.","year":"2014","unstructured":"Joseph E. Gonzalez, Reynold S. Xin, Ankur Dave, Daniel Crankshaw, Michael J. Franklin, and Ion Stoica. 2014. GraphX: Graph Processing in a Distributed Dataflow Framework. In 11th USENIX Symposium on Operating Systems Design and Implementation (OSDI 14). USENIX Association, Broomfield, CO, 599--613. https:\/\/www.usenix.org\/conference\/osdi14\/technical-sessions\/presentation\/gonzalez"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2017.2647939"},{"key":"e_1_3_2_1_40_1","volume-title":"Whiz: Data-Driven Analytics Execution. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)","author":"Grandl Robert","year":"2021","unstructured":"Robert Grandl, Arjun Singhvi, Raajay Viswanathan, and Aditya Akella. 2021. Whiz: Data-Driven Analytics Execution. In 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI 21)."},{"key":"e_1_3_2_1_41_1","volume-title":"Kaggle: Machine Learning and Data Science Community. https:\/\/www.kaggle.com\/.","year":"2023","unstructured":"Kaggle. 2023. Kaggle: Machine Learning and Data Science Community. https:\/\/www.kaggle.com\/."},{"key":"e_1_3_2_1_42_1","volume-title":"Mattson","author":"Kepner Jeremy","year":"2016","unstructured":"Jeremy Kepner, Peter Aaltonen, David A. Bader, Aydin Bulu\u00e7, Franz Franchetti, John R. Gilbert, Dylan Hutchison, Manoj Kumar, Andrew Lumsdaine, Henning Meyerhenke, Scott McMillan, Jos\u00e9 E. Moreira, John D. Owens, Carl Yang, Marcin Zalewski, and Timothy G. Mattson. 2016. Mathematical Foundations of the GraphBLAS. CoRR abs\/1606.05790 (2016). arXiv:1606.05790 http:\/\/arxiv.org\/abs\/1606.05790"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/1772690.1772751"},{"key":"e_1_3_2_1_44_1","volume-title":"Hadoop in action","author":"Lam Chuck","unstructured":"Chuck Lam. 2010. Hadoop in action. Simon and Schuster."},{"key":"e_1_3_2_1_45_1","volume-title":"MLIR: A Compiler Infrastructure for the End of Moore's Law. CoRR abs\/2002.11054","author":"Lattner Chris","year":"2020","unstructured":"Chris Lattner, Jacques A. Pienaar, Mehdi Amini, Uday Bondhugula, River Riddle, Albert Cohen, Tatiana Shpeisman, Andy Davis, Nicolas Vasilache, and Oleksandr Zinenko. 2020. MLIR: A Compiler Infrastructure for the End of Moore's Law. CoRR abs\/2002.11054 (2020). arXiv:2002.11054 https:\/\/arxiv.org\/abs\/2002.11054"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24644-2_35"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2670979.2670985"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.14778\/3415478.3415530"},{"key":"e_1_3_2_1_49_1","volume-title":"PAYSIM: A FINANCIAL MOBILE MONEY SIMULATOR FOR FRAUD DETECTION.","author":"Lopez-Rojas Edgar Alonso","year":"2016","unstructured":"Edgar Alonso Lopez-Rojas, Ahmad Elmir, and Stefan Axelsson. 2016. PAYSIM: A FINANCIAL MOBILE MONEY SIMULATOR FOR FRAUD DETECTION."},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3446804.3446844"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/1807167.1807184"},{"key":"e_1_3_2_1_52_1","unstructured":"Stephen Merity Caiming Xiong James Bradbury and Richard Socher. 2016. Pointer Sentinel Mixture Models. arXiv:1609.07843 [cs.CL]"},{"key":"e_1_3_2_1_53_1","volume-title":"Weinberger (Eds.)","volume":"26","author":"Mikolov Tomas","year":"2013","unstructured":"Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Corrado, and Jeff Dean. 2013. Distributed Representations of Words and Phrases and their Compositionality. In Advances in Neural Information Processing Systems, C.J. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K.Q. Weinberger (Eds.), Vol. 26. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/9aa42b31882ec039965f3c4923ce901b- Paper.pdf"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.14778\/3213880.3213890"},{"key":"e_1_3_2_1_55_1","volume-title":"Conference on Innovative Data Systems Research (CIDR). 45","author":"Palkar Shoumik","year":"2017","unstructured":"Shoumik Palkar, James J Thomas, Anil Shanbhag, Deepak Narayanan, Holger Pirk, Malte Schwarzkopf, Saman Amarasinghe, Matei Zaharia, and Stanford InfoLab. 2017. Weld: A common runtime for high performance data analytics. In Conference on Innovative Data Systems Research (CIDR). 45."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359652"},{"key":"e_1_3_2_1_57_1","volume-title":"Spark Parameter Tuning via Trial-and-Error. CoRR abs\/1607.07348","author":"Petridis Panagiotis","year":"2016","unstructured":"Panagiotis Petridis, Anastasios Gounaris, and Jordi Torres. 2016. Spark Parameter Tuning via Trial-and-Error. CoRR abs\/1607.07348 (2016). arXiv:1607.07348 http:\/\/arxiv.org\/abs\/1607.07348"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/224538.224655"},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1145\/2517349.2522740"},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSST.2010.5496972"},{"key":"e_1_3_2_1_61_1","unstructured":"Rajat Singh. 2018. Friends Recommender In Social Network. https:\/\/github.com\/iamsinghrajat\/Friends-Recommender-In-Social-Network."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3448016.3457244"},{"key":"e_1_3_2_1_63_1","volume-title":"Proceedings of the 13th Usenix Conference on Networked Systems Design and Implementation","author":"Venkataraman Shivaram","year":"2016","unstructured":"Shivaram Venkataraman, Zongheng Yang, Michael Franklin, Benjamin Recht, and Ion Stoica. 2016. Ernest: Efficient Performance Prediction for Large-Scale Advanced Analytics. In Proceedings of the 13th Usenix Conference on Networked Systems Design and Implementation (Santa Clara, CA) (NSDI '16). USENIX Association, USA, 363--378."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-SmartCity-DSS.2016.0088"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCC-CSS-ICESS.2015.246"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Jaewon Yang and Jure Leskovec. 2012. Defining and Evaluating Network Communities based on Ground-truth. arXiv:1205.6233 [cs.SI]","DOI":"10.1145\/2350190.2350193"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589780"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/2934664"},{"key":"e_1_3_2_1_69_1","volume-title":"Web-Age Information Management","author":"Zhang Kai","unstructured":"Kai Zhang, Qian Yu, Kai Lei, and Kuai Xu. 2014. Characterizing Tweeting Behaviors of Sina Weibo Users via Public Data Streaming. In Web-Age Information Management. Springer, 294--297."},{"key":"e_1_3_2_1_70_1","volume-title":"Gemini: A Computation-Centric Distributed Graph Processing System.. In OSDI. 301--316.","author":"Zhu Xiaowei","year":"2016","unstructured":"Xiaowei Zhu, Wenguang Chen, Weimin Zheng, and Xiaosong Ma. 2016. Gemini: A Computation-Centric Distributed Graph Processing System.. In OSDI. 301--316."},{"key":"e_1_3_2_1_71_1","volume-title":"Livegraph: A transactional graph storage system with purely sequential adjacency list scans. arXiv preprint arXiv:1910.05773","author":"Zhu Xiaowei","year":"2019","unstructured":"Xiaowei Zhu, Guanyu Feng, Marco Serafini, Xiaosong Ma, Jiping Yu, Lei Xie, Ashraf Aboulnaga, and Wenguang Chen. 2019. Livegraph: A transactional graph storage system with purely sequential adjacency list scans. arXiv preprint arXiv:1910.05773 (2019)."},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3588921"}],"event":{"name":"EuroSys '25: Twentieth European Conference on Computer Systems","location":"Rotterdam Netherlands","acronym":"EuroSys '25","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the Twentieth European Conference on Computer Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689031.3696100","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3689031.3696100","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T11:25:08Z","timestamp":1755775508000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3689031.3696100"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,30]]},"references-count":72,"alternative-id":["10.1145\/3689031.3696100","10.1145\/3689031"],"URL":"https:\/\/doi.org\/10.1145\/3689031.3696100","relation":{},"subject":[],"published":{"date-parts":[[2025,3,30]]},"assertion":[{"value":"2025-03-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}