arrow
返回

OmniSketch: Multi-dimensional update stream analytics with arbitrary predicates

delete2026-01-10
delete0
delete
OA
AI
W
Wieger R. Punter *
O
Odysseas Papapetrou
M
Minos Garofalakis
DOI:10.1007/s00778-025-00960-6delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
A key need in different disciplines is to perform analytics over fast-paced data streams, similar in nature to the traditional OLAP analytics in relational databases - i.e., with aggregates and selection predicates. Storing unbounded streams, however, is not a realistic, or desired approach due to the high storage requirements, and the delays introduced when storing massive data. Accordingly, many synopses/sketches have been proposed that can summarize the stream in small memory (usually sufficiently small to be stored in RAM), such that aggregate queries can be efficiently approximated, without storing the full stream. However, past synopses predominantly focus on summarizing single-attribute streams, and cannot handle selection predicates and constraints on arbitrary subsets of multiple attributes efficiently. In this work, we propose OmniSketch, the first sketch that scales to fast-paced and complex data streams (with many attributes), and supports count aggregates with predicates on multiple attributes, dynamically chosen at query time. OmniSketch supports streams containing both inserts and deletes, under the bounded deletes streaming model. OmniSketch offers probabilistic guarantees, a favorable space-accuracy tradeoff, and a worst-case logarithmic complexity for updating and for query execution. We demonstrate experimentally with both real and synthetic data that OmniSketch outperforms the state-of-the-art and can approximate complex ad-hoc queries within the configured accuracy guarantees, with small memory requirements.
Keyword:
Multi-dimensional Stream Analytics
Sketching
Bounded deletes model
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

T
The VLDB Journal
IF:
0
论文数:
36
被引数:
0

机构

A
athena research center
学者数:
47
论文数: 23
被引数: 0
E
Eindhoven University of Technology
学者数:
1.6W
论文数: 1.5W
被引数: 2.2W
引用论文

引用论文

Tracking set-expression cardinalities over continuous update streams
err2004-12-01
err0
PREAI
errSumit Ganguly; Minos Garofalakis; Rajeev Rastogi
err分享
err收藏
err分享
err收藏
Enabling efficient and general subpopulation analytics in multidimensional data streams
err2022-07-01
err0
PREAI
errManousis,Antonis; Cheng,Zhuo; Basat,Ran Ben; Liu,Zaoxing; Sekar,Vyas
err分享
err收藏
One Sketch to Rule Them All
err2016-08-22
err0
errOAAI
errZaoxing Liu; Antonis Manousis; Gregory Vorsanger; Vyas Sekar; Vladimir Braverman
err分享
err收藏
err分享
err收藏
SciPy 1.0: fundamental algorithms for scientific computing in PythonSciPy 1.0: Python中科学计算的基本算法
err2020-02-03
err2.1W
errOAAI
errVirtanen, Pauli; Gommers, Ralf; Oliphant, Travis E.; Haberland, Matt; Reddy, Tyler; Cournapeau, David; Burovski, Evgeni; Peterson, Pearu; Weckesser, Warren; Bright, Jonathan; van der Walt, Stefan J.; Brett, Matthew; Wilson, Joshua; Millman, K. Jarrod; Mayorov, Nikolay; Nelson, Andrew R. J.; Jones, Eric; Kern, Robert; Larson, Eric; Carey, C. J.; Polat, Ilhan; Feng, Yu; Moore, Eric W.; VanderPlas, Jake; Laxalde, Denis; Perktold, Josef; Cimrman, Robert; Henriksen, Ian; Quintero, E. A.; Harris, Charles R.; Archibald, Anne M.; Ribeiro, Antonio H.; Pedregosa, Fabian; van Mulbregt, Paul
err分享
err收藏
学者 查看更多内容