Filters








27,339 Hits in 8.3 sec

Predicting Multiple Metrics for Queries: Better Decisions Enabled by Machine Learning

Archana Ganapathi, Harumi Kuno, Umeshwar Dayal, Janet L. Wiener, Armando Fox, Michael Jordan, David Patterson
2009 Proceedings / International Conference on Data Engineering  
We have developed a system that uses machine learning to accurately predict the performance metrics of database queries whose execution times range from milliseconds to hours.  ...  We were able to predict individual query elapsed time within 20% of its actual time for 85% of the test queries.  ...  The simultaneous predictability of multiple performance metrics using our approach enabled us to better understand inaccurate predictions.  ... 
doi:10.1109/icde.2009.130 dblp:conf/icde/GanapathiKDWFJP09 fatcat:6u3svo2d3jei3cwgxhrfat5die

Processing Forecasting Queries

Songyun Duan, Shivnath Babu
2007 Very Large Data Bases Conference  
Fa supports efficient algorithms to generate execution plans automatically for forecasting queries from a novel plan space comprising operators for transforming data, learning statistical models from data  ...  , and doing inference using the learned models.  ...  The design of FPS has been influenced by recent comparison studies on synopses and transformations done by the machine-learning community [4, 10, 19] .  ... 
dblp:conf/vldb/DuanB07 fatcat:2cf6rui3inchvjfv6worupoi34

Bao: Learning to Steer Query Optimizers [article]

Ryan Marcus, Parimarjan Negi, Hongzi Mao, Nesime Tatbul, Mohammad Alizadeh, Tim Kraska
2020 arXiv   pre-print
Recent efforts to apply machine learning techniques to query optimization challenges have been promising, but have shown few practical gains due to substantive training overhead, inability to adapt to  ...  Bao takes advantage of the wisdom built into existing query optimizers by providing per-query optimization hints.  ...  For example, multiple cardinality estimates from different estimators or predictions from learned cost models may be added.  ... 
arXiv:2004.03814v1 fatcat:zprpgewcsbfzzfpz5iscxh7yai

Learning-based SPARQL query performance modeling and prediction

Wei Emma Zhang, Quan Z. Sheng, Yongrui Qin, Kerry Taylor, Lina Yao
2017 World wide web (Bussum)  
Further, the effort exploiting machine learning techniques is limited. In this paper, we adopt machine learning techniques to predict the performance of SPARQL queries.  ...  We adopt multiple regression models as prediction models and propose an one-step and an two-step prediction processes. Query performances in both cold and warm stages are studied.  ...  Conclusion To conclude, we leverage machine learning techniques to predict multiple performance metrics for SPARQL queries. We transform a given SPARQL query to a vector representation.  ... 
doi:10.1007/s11280-017-0498-1 fatcat:2mmbwvizwrgctcsg723pf5feeq

Web search query privacy: Evaluating query obfuscation and anonymizing networks1

Sai Teja Peddinti, Nitesh Saxena
2014 Journal of Computer Security  
We demonstrate that a search engine, equipped with only a short-term history of a user's search queries, can break the privacy guarantees of TMN and Tor by only utilizing off-the-shelf machine learning  ...  A fundamental problem with these solutions, however, is that user queries are still obviously revealed to the search engine, although they are "mixed" among queries generated either by a machine or by  ...  We also thank Lisa Hellerstein for discussion on machine learning classifiers and her helpful comments on our work, and the developers of TMN -Helen Nissenbaum and Vincent Toubiana -for their useful suggestions  ... 
doi:10.3233/jcs-130491 fatcat:az66itfapjeipgaleogzdf6brq

Forecasting SQL Query Cost at Twitter [article]

Chunxu Tang, Beinan Wang, Zhenxiao Luo, Huijun Wu, Shajan Dasan, Maosong Fu, Yao Li, Mainak Ghosh, Ruchin Kabra, Nikhil Kantibhai Navadiya, Da Cheng, Fred Dai (+2 others)
2022 arXiv   pre-print
The models can achieve 97.9\% accuracy for CPU usage prediction and 97\% accuracy for memory usage prediction.  ...  Can we estimate the cost of each query more efficiently without any computation in a SQL engine kernel? Can machine learning techniques help to estimate SQL query resource utilization?  ...  ACKNOWLEDGMENT We would like to express our gratitude to everyone who has served on Twitter's Interactive Query team, including former team members Hao Luo and Yaliang Wang.  ... 
arXiv:2204.05529v1 fatcat:3o6hc42whraetjtud6m6uzuiia

Deep Search Query Intent Understanding [article]

Xiaowei Liu, Weiwei Guo, Huiji Gao, Bo Long
2020 arXiv   pre-print
Accurate query intent prediction allows the search engine to better serve the user's need by rendering results from more relevant categories.  ...  Various deep learning components for query text understanding are experimented.  ...  The proposed deep learning based models are proven to be effective and efficient for online search applications.  ... 
arXiv:2008.06759v2 fatcat:iy3gor7kl5fzlj5icpefnjj4wm

Optimizing queries to remote resources

Albert Weichselbraun
2010 Journal of Intelligent Information Systems  
This paper suggests a cost and utility model for optimizing such queries by leveraging optimal stopping theory from business economics: applications are modeled as decision makers that look for optimal  ...  Recent research in this area focuses on the integration of multiple data sources to facilitate tasks such as ontology learning, user query expansion and context recognition.  ...  Acknowledgment The project results have been developed in the RAVEN (Relation Analysis and Visualization) project funded by the Austrian Ministry of Transport, Innovation and Technology and  ... 
doi:10.1007/s10844-010-0129-0 fatcat:y4kb6thnffdfroirp4spefd3si

Query by Semantic Example [chapter]

Nikhil Rasiwasia, Nuno Vasconcelos, Pedro J. Moreno
2006 Lecture Notes in Computer Science  
Cox et al. [26] also focus on the task of learning a predictive model for user selections, by learning a mapping between 1) the image selection patterns made by users instructed to consider visual similarity  ...  This suggests that a better estimate of the query SMN should be possible by considering a set of multiple query images.In addition to higher accuracy, a set of multiple queries is also likely to have better  ... 
doi:10.1007/11788034_6 fatcat:du3zk6dfvnbatmykk7csqot34q

Crowdsourced enumeration queries

B. Trushkowsky, T. Kraska, M. J. Franklin, P. Sarkar
2013 2013 IEEE 29th International Conference on Data Engineering (ICDE)  
Hybrid human/computer database systems promise to greatly expand the usefulness of query processing by incorporating the crowd for data gathering and other tasks.  ...  To address these issues, we develop statistical tools that enable users and systems developers to reason about query completeness.  ...  This research is supported in part by a National Science Foundation graduate fellowship, in part by NSF CISE Expeditions award CCF-1139158, and gifts from Amazon Web Services, Google, SAP, Blue Goji, Cisco  ... 
doi:10.1109/icde.2013.6544865 dblp:conf/icde/TrushkowskyKFS13 fatcat:x2hyka745zamzftmnwcmvdcjmy

Robust query processing

Goetz Graefe
2011 2011 IEEE 27th International Conference on Data Engineering  
were contributed by some participants.  ...  discussion and collaboration regarding causes, opportunities, and solutions for achieving robust query processing.  ...  with complex expressions and appropriate metrics, as well as reasons, metrics and benchmarks for risk in query optimization decisions.  ... 
doi:10.1109/icde.2011.5767961 dblp:conf/icde/Graefe11 fatcat:7jwx6qukinbvlad4df2a5aumgq

Query-Driven Multi-Instance Learning

Yen-Chi Hsu, Cheng-Yao Hong, Ming-Sui Lee, Tyng-Luh Liu
2020 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
To learn a deep-net model for qMIL, we construct a network component that achieves a generalized compatibility measure for query-visual co-embedding and yields proper instance attentions to the given query  ...  We introduce a query-driven approach (qMIL) to multi-instance learning where the queries aim to uncover the class labels embodied in a given bag of instances.  ...  This work was supported in part by the MOST, Taiwan under Grant 108-2634-F-001-007.  ... 
doi:10.1609/aaai.v34i04.5836 fatcat:piij377peffcdofjcbzdvdxisa

IMPROVE Visiolinguistic Performance with Re-Query [article]

Stephan J. Lemmer, Jason J. Corso
2022 arXiv   pre-print
Of Verbal Expressions (IMPROVE) – a re-query method that updates the model's prediction across multiple queries.  ...  Through the exemplar task of referring expression comprehension, we formalize and motivate the problem, introduce an evaluation method, and propose Iterative Multiplication of Probabilities for Re-query  ...  upper limit imposed by the metric of coverage.  ... 
arXiv:2110.10206v2 fatcat:fdsnlw7ujfdyjb3agf4znm4jmu

Self-tuning query mesh for adaptive multi-route query processing

Rimma V. Nehme, Elke A. Rundensteiner, Elisa Bertino
2009 Proceedings of the 12th International Conference on Extending Database Technology Advances in Database Technology - EDBT '09  
ST-QM addresses adaptive query processing by abstracting it as a concept drift problem -a wellknown subject in machine learning.  ...  In this work, we fill this gap by proposing a Self-Tuning Query Mesh (ST-QM ) -an adaptive solution for content-based multi-plan execution engines.  ...  machine learning alike [16] .  ... 
doi:10.1145/1516360.1516452 dblp:conf/edbt/NehmeRB09 fatcat:md2ivbw2vbe47kdk537e2fuwxe

Deploying a Steered Query Optimizer in Production at Microsoft

Wangda Zhang, Matteo Interlandi, Paul Mineiro, Shi Qiao, Nasim Ghazanfari, Karlen Lie, Marc Friedman, Rafah Hosn, Hiren Patel, Alekh Jindal
2022 Proceedings of the 2022 International Conference on Management of Data  
Our resulting system, QO-Advisor, essentially externalizes the query planner to a massive offline pipeline for better exploration and specialization.  ...  We discuss various aspects of our design and show detailed results over production SCOPE workloads at Microsoft, where the system is currently enabled by default.  ...  ACKNOWLEDGMENTS We would like to thank Carlo Curino, John Langford, Raghu Ramakrishnan, and Siddhartha Sen for their insightful feedback, as well as GT Ni for the work during early stages of the development  ... 
doi:10.1145/3514221.3526052 fatcat:bvpga6in7jblzo7bms3ta4daje
« Previous Showing results 1 — 15 out of 27,339 results