Optimizing machine learning inference queries with correlative proxy models

Author:

Yang Zhihui1,Wang Zuozhi2,Huang Yicong2,Lu Yao3,Li Chen2,Wang X. Sean4

Affiliation:

1. Zhejiang Lab, Hangzhou, China

2. UC Irvine

3. Microsoft Research

4. Fudan University, Shanghai, China

Abstract

We consider accelerating machine learning (ML) inference queries on unstructured datasets. Expensive operators such as feature extractors and classifiers are deployed as user-defined functions (UDFs), which are not penetrable with classic query optimization techniques such as predicate push-down. Recent optimization schemes (e.g., Probabilistic Predicates or PP) assume independence among the query predicates, build a proxy model for each predicate offline, and rewrite a new query by injecting these cheap proxy models in the front of the expensive ML UDFs. In such a manner, unlikely inputs that do not satisfy query predicates are filtered early to bypass the ML UDFs. We show that enforcing the independence assumption in this context may result in sub-optimal plans. In this paper, we propose CORE, a query optimizer that better exploits the predicate correlations and accelerates ML inference queries. Our solution builds the proxy models online for a new query and leverages a branch-and-bound search process to reduce the building costs. Results on three real-world text, image and video datasets show that CORE improves the query throughput by up to 63% compared to PP and up to 80% compared to running the queries as it is.

Publisher

Association for Computing Machinery (ACM)

Subject

General Earth and Planetary Sciences,Water Science and Technology,Geography, Planning and Development

Reference42 articles.

1. Pankaj K Agarwal , Sariel Har-Peled , and Kasturi R Varadarajan . 2005. Geometric approximation via coresets. Combinatorial and computational geometry 52 ( 2005 ), 1--30. Pankaj K Agarwal, Sariel Har-Peled, and Kasturi R Varadarajan. 2005. Geometric approximation via coresets. Combinatorial and computational geometry 52 (2005), 1--30.

2. Adaptive ordering of pipelined stream filters

3. Model slicing for supporting complex analytics with elastic inference cost and resource constraints

4. Zhaowei Cai , Mohammad J. Saberian , and Nuno Vasconcelos . 2015 . Learning Complexity-Aware Cascades for Deep Pedestrian Detection. In 2015 IEEE International Conference on Computer Vision, ICCV 2015 , December 7-13, 2015. IEEE Computer Society, Santiago, Chile, 3361--3369. Zhaowei Cai, Mohammad J. Saberian, and Nuno Vasconcelos. 2015. Learning Complexity-Aware Cascades for Deep Pedestrian Detection. In 2015 IEEE International Conference on Computer Vision, ICCV 2015, December 7-13, 2015. IEEE Computer Society, Santiago, Chile, 3361--3369.

5. Approximate Query Processing

Cited by 10 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3