Detect, Distill and Update: Learned DB Systems Facing Out of Distribution Data

Author:

Kurmanji Meghdad1ORCID,Triantafillou Peter1ORCID

Affiliation:

1. University of Warwick, Coventry, United Kingdom

Abstract

Machine Learning (ML) is changing DBs as many DB components are being replaced by ML models. One open problem in this setting is how to update such ML models in the presence of data updates. We start this investigation focusing on data insertions (dominating updates in analytical DBs). We study how to update neural network (NN) models when new data follows a different distribution (a.k.a. it is "out-of-distribution" -- OOD), rendering previously-trained NNs inaccurate. A requirement in our problem setting is that learned DB components should ensure high accuracy for tasks on old and new data (e.g., for approximate query processing (AQP), cardinality estimation (CE), synthetic data generation (DG), etc.). This paper proposes a novel updatability framework (DDUp). DDUp can provide updatability for different learned DB system components, even based on different NNs, without the high costs to retrain the NNs from scratch. DDUp entails two components: First, a novel, efficient, and principled statistical-testing approach to detect OOD data. Second, a novel model updating approach, grounded on the principles of transfer learning with knowledge distillation, to update learned models efficiently, while still ensuring high accuracy. We develop and showcase DDUp's applicability for three different learned DB components, AQP, CE, and DG, each employing a different type of NN. Detailed experimental evaluation using real and benchmark datasets for AQP, CE, and DG detail DDUp's performance advantages.

Funder

EPSRC

Huawei IRC

Publisher

Association for Computing Machinery (ACM)

Reference85 articles.

1. Expert Gate: Lifelong Learning with a Network of Experts

2. Manuel Baena-Garcia , José del Campo-Ávila , Raúl Fidalgo , Albert Bifet , R Gavalda , and Rafael Morales-Bueno . 2006 . Early drift detection method . In Fourth international workshop on knowledge discovery from data streams , Vol. 6 . 77--86. Manuel Baena-Garcia, José del Campo-Ávila, Raúl Fidalgo, Albert Bifet, R Gavalda, and Rafael Morales-Bueno. 2006. Early drift detection method. In Fourth international workshop on knowledge discovery from data streams, Vol. 6. 77--86.

3. On a new multivariate two-sample test

4. Li Bu , Cesare Alippi , and Dongbin Zhao . 2016. A pdf-free change detection test based on density difference estimation . IEEE transactions on neural networks and learning systems, Vol. 29 , 2 ( 2016 ), 324--334. Li Bu, Cesare Alippi, and Dongbin Zhao. 2016. A pdf-free change detection test based on density difference estimation. IEEE transactions on neural networks and learning systems, Vol. 29, 2 (2016), 324--334.

5. End-to-End Incremental Learning

Cited by 11 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

1. Machine Learning for Databases: Foundations, Paradigms, and Open problems;Companion of the 2024 International Conference on Management of Data;2024-06-09

2. Learned Query Optimizer: What is New and What is Next;Companion of the 2024 International Conference on Management of Data;2024-06-09

3. MFIX: An Efficient and Reliable Index Advisor via Multi-Fidelity Bayesian Optimization;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

4. TRAP: Tailored Robustness Assessment for Index Advisors via Adversarial Perturbation;2024 IEEE 40th International Conference on Data Engineering (ICDE);2024-05-13

5. Machine Unlearning in Learned Databases: An Experimental Analysis;Proceedings of the ACM on Management of Data;2024-03-12

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