A Comparison of Top-k Threshold Estimation Techniques for Disjunctive Query Processing
A Comparison of Top-k Threshold Estimation Techniques for Disjunctive Query Processing
复制标题
用于析取查询处理的 Top-k 阈值估计技术的比较
DOI：
10.1145/3340531.3412080
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Torsten Suel
中科院分区：
文献类型：
--
作者：
Antonio Mallia;Michal Siedlaczek;Mengyang Sun;Torsten Suel
在top-k阈值估计问题中，给定查询q，目标是估计结果在排名k处的得分。对该分数的良好估计可以显著提高几种查询处理场景的性能，包括选择性搜索、索引分层和广泛使用的析取查询处理算法（如MaxScore、WAND和BMW）。已经提出了几种方法，包括参数方法，使用随机采样的方法，以及最近的基于机器学习的方法。然而，之前的工作未能对这些方法进行任何实验比较。在本文中，我们解决这个问题，通过重新实现四个主要的方法，并比较它们的估计误差，运行时间，高估的可能性，和端到端的性能时，适用于常见的类的析取top-k查询处理算法。
In the top-k threshold estimation problem, given a query q, the goal is to estimate the score of the result at rank k. A good estimate of this score can result in significant performance improvements for several query processing scenarios, including selective search, index tiering, and widely used disjunctive query processing algorithms such as MaxScore, WAND, and BMW. Several approaches have been proposed, including parametric approaches, methods using random sampling, and a recent approach based on machine learning. However, previous work fails to perform any experimental comparison between these approaches. In this paper, we address this issue by reimplementing four major approaches and comparing them in terms of estimation error, running time, likelihood of an overestimate, and end-to-end performance when applied to common classes of disjunctive top-k query processing algorithms.
速度更快的 BlockMax WAND，跳跃时间更长
DOI：
10.1007/978-3-030-15712-8_52
发表时间：
2019
期刊：
European Conference on Information Retrieval
影响因子：
--
作者：
Mallia, Antonio;Porciani, Elia
通讯作者：
Porciani, Elia