{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T04:57:32Z","timestamp":1755838652389},"reference-count":53,"publisher":"Association for Computing Machinery (ACM)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. VLDB Endow."],"published-print":{"date-parts":[[2017,11]]},"abstract":"<jats:p>\n            Machine learning (ML) over relational data is a booming area of data management. While there is a lot of work on scalable and fast ML systems, little work has addressed the pains of\n            <jats:italic>sourcing<\/jats:italic>\n            data for ML tasks. Real-world relational databases typically have many tables (often, dozens) and data scientists often struggle to even obtain all tables for joins before ML. In this context, Kumar et al. showed recently that key-foreign key dependencies (KFKDs) between tables often lets us avoid such joins without significantly affecting prediction accuracy-an idea they called \"avoiding joins safely.\" While initially controversial, this idea has since been used by multiple companies to reduce the burden of data sourcing for ML. But their work applied only to linear classifiers. In this work, we verify if their results hold for three popular high-capacity classifiers: decision trees, non-linear SVMs, and ANNs. We conduct an extensive experimental study using both real-world datasets and simulations to analyze the effects of avoiding KFK joins on such models. Our results show that these high-capacity classifiers are surprisingly and counter-intuitively more robust to avoiding KFK joins compared to linear classifiers, refuting an intuition from the prior work's analysis. We explain this behavior intuitively and identify open questions at the intersection of data management and ML theoretical research. All of our code and datasets are available for download from http:\/\/cseweb.ucsd.edu\/~arunkk\/hamlet.\n          <\/jats:p>","DOI":"10.14778\/3157794.3157804","type":"journal-article","created":{"date-parts":[[2017,12,12]],"date-time":"2017-12-12T18:33:38Z","timestamp":1513103618000},"page":"366-379","source":"Crossref","is-referenced-by-count":17,"title":["Are key-foreign key joins safe to avoid when learning high-capacity classifiers?"],"prefix":"10.14778","volume":"11","author":[{"given":"Vraj","family":"Shah","sequence":"first","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arun","family":"Kumar","sequence":"additional","affiliation":[{"name":"University of California"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojin","family":"Zhu","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2017,11]]},"reference":[{"key":"e_1_2_1_1_1","volume-title":"Facebook friend recommendation system","unstructured":"Personal communications : Facebook friend recommendation system ; LogicBlox retail analytics; MakeMyTrip customer analytics. Personal communications: Facebook friend recommendation system; LogicBlox retail analytics; MakeMyTrip customer analytics."},{"key":"e_1_2_1_2_1","unstructured":"Nature News. https:\/\/www.nature.com\/articles\/d41586-017-02190-5.  Nature News. https:\/\/www.nature.com\/articles\/d41586-017-02190-5."},{"key":"e_1_2_1_3_1","volume-title":"Foundations of Databases: The Logical Level","author":"Abiteboul S.","year":"1995","unstructured":"S. Abiteboul , R. Hull , and V. Vianu , editors . Foundations of Databases: The Logical Level . Addison-Wesley Longman Publishing Co., Inc. , Boston, MA, USA , 1 st edition, 1995 . S. Abiteboul, R. Hull, and V. Vianu, editors. Foundations of Databases: The Logical Level. Addison-Wesley Longman Publishing Co., Inc., Boston, MA, USA, 1st edition, 1995.","edition":"1"},{"key":"e_1_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.5555\/891073"},{"key":"e_1_2_1_5_1","volume-title":"CIDR","author":"Anderson M.","year":"2013","unstructured":"M. Anderson , D. Antenucci , V. Bittorf , M. Burgess , M. J. Cafarella , A. Kumar , F. Niu , Y. Park , C. R\u00e9 , and C. Zhang . Brainwash: A Data System for Feature Engineering . In CIDR , 2013 . M. Anderson, D. Antenucci, V. Bittorf, M. Burgess, M. J. Cafarella, A. Kumar, F. Niu, Y. Park, C. R\u00e9, and C. Zhang. Brainwash: A Data System for Feature Engineering. In CIDR, 2013."},{"key":"e_1_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.14778\/3007263.3007279"},{"key":"e_1_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.5555\/646418.693349"},{"key":"e_1_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.5555\/2029604.2029642"},{"key":"e_1_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.5555\/2401764"},{"key":"e_1_2_1_10_1","volume-title":"Proceedings of 17th International Conference on Machine Learning","author":"Domingos P.","year":"2000","unstructured":"P. Domingos . A Unified Bias-Variance Decomposition and its Applications . In Proceedings of 17th International Conference on Machine Learning , 2000 . P. Domingos. A Unified Bias-Variance Decomposition and its Applications. In Proceedings of 17th International Conference on Machine Learning, 2000."},{"key":"e_1_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536222.2536253"},{"key":"e_1_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/2213836.2213874"},{"key":"e_1_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2948674.2948675"},{"key":"e_1_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/1386352.1386373"},{"key":"e_1_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.5555\/1296231"},{"key":"e_1_2_1_16_1","volume-title":"Feature Extraction: Foundations and Applications","author":"Guyon I.","year":"2001","unstructured":"I. Guyon , S. Gunn , M. Nikravesh , and L. A. Zadeh . Feature Extraction: Foundations and Applications . New York : Springer-Verlag , 2001 . I. Guyon, S. Gunn, M. Nikravesh, and L. A. Zadeh. Feature Extraction: Foundations and Applications. New York: Springer-Verlag, 2001."},{"key":"e_1_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-21606-5"},{"key":"e_1_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.14778\/2367502.2367510"},{"key":"e_1_2_1_19_1","volume-title":"CIDR","author":"Hellerstein J. M.","year":"2017","unstructured":"J. M. Hellerstein , V. Sreekanti , J. E. Gonzalez , J. Dalton , A. Dey , S. Nag , K. Ramachandran , S. Arora , A. Bhattacharyya , and S. Das . Ground: A Data Context Service . In CIDR , 2017 . J. M. Hellerstein, V. Sreekanti, J. E. Gonzalez, J. Dalton, A. Dey, S. Nag, K. Ramachandran, S. Arora, A. Bhattacharyya, and S. Das. Ground: A Data Context Service. In CIDR, 2017."},{"key":"e_1_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1198\/106186006X133933"},{"key":"e_1_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2788621"},{"key":"e_1_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2011.08.001"},{"key":"e_1_2_1_23_1","article-title":"Data Scientists in Software Teams: State of the Art and Challenges","author":"Kim M.","year":"2017","unstructured":"M. Kim , T. Zimmermann , R. DeLine , and A. Begel . Data Scientists in Software Teams: State of the Art and Challenges . IEEE Transactions on Software Engineering, PP(99) , 2017 . M. Kim, T. Zimmermann, R. DeLine, and A. Begel. Data Scientists in Software Teams: State of the Art and Challenges. IEEE Transactions on Software Engineering, PP(99), 2017.","journal-title":"IEEE Transactions on Software Engineering, PP(99)"},{"key":"e_1_2_1_24_1","volume-title":"Adam: A Method for Stochastic Optimization. In 3rd International Conference for Learning Representations (ICLR)","author":"Kingma D. P.","year":"2015","unstructured":"D. P. Kingma and J. Ba . Adam: A Method for Stochastic Optimization. In 3rd International Conference for Learning Representations (ICLR) , 2015 . D. P. Kingma and J. Ba. Adam: A Method for Stochastic Optimization. In 3rd International Conference for Learning Representations (ICLR), 2015."},{"key":"e_1_2_1_25_1","volume-title":"ICML","author":"Koller D.","year":"1995","unstructured":"D. Koller and M. Sahami . Toward Optimal Feature Selection . In ICML , 1995 . D. Koller and M. Sahami. Toward Optimal Feature Selection. In ICML, 1995."},{"key":"e_1_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.14778\/2536274.2536302"},{"key":"e_1_2_1_27_1","volume-title":"CIDR","author":"Kraska T.","year":"2013","unstructured":"T. Kraska , A. Talwalkar , J. C. Duchi , R. Griffith , M. J. Franklin , and M. I. Jordan . MLbase: A Distributed Machine-learning System . In CIDR , 2013 . T. Kraska, A. Talwalkar, J. C. Duchi, R. Griffith, M. J. Franklin, and M. I. Jordan. MLbase: A Distributed Machine-learning System. In CIDR, 2013."},{"key":"e_1_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824087"},{"key":"e_1_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/2723372.2723713"},{"key":"e_1_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882952"},{"key":"e_1_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM.2015.7359925"},{"key":"e_1_2_1_32_1","volume-title":"UAI","author":"Low Y.","year":"2010","unstructured":"Y. Low , J. E. Gonzalez , A. Kyrola , D. Bickson , C. E. Guestrin , and J. Hellerstein . GraphLab: A New Framework For Parallel Machine Learning . In UAI , 2010 . Y. Low, J. E. Gonzalez, A. Kyrola, D. Bickson, C. E. Guestrin, and J. Hellerstein. GraphLab: A New Framework For Parallel Machine Learning. In UAI, 2010."},{"key":"e_1_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.5555\/541177"},{"key":"e_1_2_1_34_1","volume-title":"AAAI","author":"Pearl J.","year":"1987","unstructured":"J. Pearl and T. Verma . The Logic of Representing Dependencies by Directed Graphs . In AAAI , 1987 . J. Pearl and T. Verma. The Logic of Representing Dependencies by Directed Graphs. In AAAI, 1987."},{"key":"e_1_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1145\/3035918.3054782"},{"key":"e_1_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1024099825458"},{"key":"e_1_2_1_37_1","volume-title":"Database Management Systems","author":"Ramakrishnan R.","year":"2003","unstructured":"R. Ramakrishnan and J. Gehrke . Database Management Systems . McGraw-Hill, Inc. , 2003 . R. Ramakrishnan and J. Gehrke. Database Management Systems. McGraw-Hill, Inc., 2003."},{"key":"e_1_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.14778\/2535573.2488340"},{"key":"e_1_2_1_39_1","volume-title":"Introducing CloudLab: Scientific Infrastructure for Advancing Cloud Architectures and Applications","author":"Ricci R.","year":"2014","unstructured":"R. Ricci , E. Eide , and C. Team . Introducing CloudLab: Scientific Infrastructure for Advancing Cloud Architectures and Applications . ; login:: the magazine of USENIX & SAGE , 39(6):36--38, 2014 . R. Ricci, E. Eide, and C. Team. Introducing CloudLab: Scientific Infrastructure for Advancing Cloud Architectures and Applications. ; login:: the magazine of USENIX & SAGE, 39(6):36--38, 2014."},{"key":"e_1_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/564376.564421"},{"key":"e_1_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/2882903.2882939"},{"key":"e_1_2_1_42_1","volume-title":"SE4ML: Software Engineering for Machine Learning (NIPS 2014 Workshop)","author":"Sculley D.","year":"2014","unstructured":"D. Sculley , G. Holt , D. Golovin , E. Davydov , T. Phillips , D. Ebner , V. Chaudhary , M. Young , J.-F. Crespo , and D. Dennison . Machine Learning: The High Interest Credit Card of Technical Debt . In SE4ML: Software Engineering for Machine Learning (NIPS 2014 Workshop) , 2014 . D. Sculley, G. Holt, D. Golovin, E. Davydov, T. Phillips, D. Ebner, V. Chaudhary, M. Young, J.-F. Crespo, and D. Dennison. Machine Learning: The High Interest Credit Card of Technical Debt. In SE4ML: Software Engineering for Machine Learning (NIPS 2014 Workshop), 2014."},{"key":"e_1_2_1_43_1","unstructured":"V. Shah A. Kumar and X. Zhu. Are Key-Foreign Key Joins Safe to Avoid when Learning High-Capacity Classifiers? (Technical Report). http:\/\/cseweb.ucsd.edu\/~arunkk\/hamlet.  V. Shah A. Kumar and X. Zhu. Are Key-Foreign Key Joins Safe to Avoid when Learning High-Capacity Classifiers? (Technical Report). http:\/\/cseweb.ucsd.edu\/~arunkk\/hamlet."},{"key":"e_1_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781107298019"},{"key":"e_1_2_1_45_1","volume-title":"Database Systems Concepts","author":"Silberschatz A.","year":"2006","unstructured":"A. Silberschatz , H. Korth , and S. Sudarshan . Database Systems Concepts . McGraw-Hill, Inc. , New York, NY, USA , 5 edition, 2006 . A. Silberschatz, H. Korth, and S. Sudarshan. Database Systems Concepts. McGraw-Hill, Inc., New York, NY, USA, 5 edition, 2006."},{"key":"e_1_2_1_46_1","volume-title":"A Novel Feature Selection Approach: Combining Feature Wrappers and Filters. Information Sciences, 177(2)","author":"Uncu O.","year":"2007","unstructured":"O. Uncu and I. Turksen . A Novel Feature Selection Approach: Combining Feature Wrappers and Filters. Information Sciences, 177(2) , 2007 . O. Uncu and I. Turksen. A Novel Feature Selection Approach: Combining Feature Wrappers and Filters. Information Sciences, 177(2), 2007."},{"key":"e_1_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.5555\/211359"},{"key":"e_1_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553516"},{"key":"e_1_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.5555\/2074158.2074222"},{"key":"e_1_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/11615576_9"},{"key":"e_1_2_1_51_1","article-title":"Efficient Feature Selection via Analysis of Relevance and Redundancy","volume":"5","author":"Yu L.","year":"2004","unstructured":"L. Yu and H. Liu . Efficient Feature Selection via Analysis of Relevance and Redundancy . Journal of Machine Learning Research , 5 , Dec. 2004 . L. Yu and H. Liu. Efficient Feature Selection via Analysis of Relevance and Redundancy. Journal of Machine Learning Research, 5, Dec. 2004.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_2_1_52_1","volume-title":"Understanding Deep Learning Requires Rethinking Generalization. In International Conference on Learning Representations (ICLR)","author":"Zhang C.","year":"2017","unstructured":"C. Zhang , S. Bengio , M. Hardt , B. Recht , and O. Vinyals . Understanding Deep Learning Requires Rethinking Generalization. In International Conference on Learning Representations (ICLR) , 2017 . C. Zhang, S. Bengio, M. Hardt, B. Recht, and O. Vinyals. Understanding Deep Learning Requires Rethinking Generalization. In International Conference on Learning Representations (ICLR), 2017."},{"key":"e_1_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDE.2010.5447819"}],"container-title":["Proceedings of the VLDB Endowment"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.14778\/3157794.3157804","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,28]],"date-time":"2022-12-28T09:38:26Z","timestamp":1672220306000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.14778\/3157794.3157804"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,11]]},"references-count":53,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2017,11]]}},"alternative-id":["10.14778\/3157794.3157804"],"URL":"https:\/\/doi.org\/10.14778\/3157794.3157804","relation":{},"ISSN":["2150-8097"],"issn-type":[{"value":"2150-8097","type":"print"}],"subject":[],"published":{"date-parts":[[2017,11]]}}}