Conditional Generative Model Based Predicate-Aware Query Approximation

Abstract

The goal of Approximate Query Processing (AQP) is to provide very fast but "accurate enough" results for costly aggregate queries thereby improving user experience in interactive exploration of large datasets. Recently proposed Machine-Learning-based AQP techniques can provide very low latency as query execution only involves model inference as compared to traditional query processing on database clusters. However, with increase in the number of filtering predicates (WHERE clauses), the approximation error significantly increases for these methods. Analysts often use queries with a large number of predicates for insights discovery. Thus, maintaining low approximation error is important to prevent analysts from drawing misleading conclusions. In this paper, we propose ELECTRA, a predicate-aware AQP system that can answer analytics-style queries with a large number of predicates with much smaller approximation errors. ELECTRA uses a conditional generative model that learns the conditional distribution of the data and at run-time generates a small (≈ 1000 rows) but representative sample, on which the query is executed to compute the approximate result. Our evaluations with four different baselines on three real-world datasets show that ELECTRA provides lower AQP error for large number of predicates compared to baselines.

Reinforced Approximate Exploratory Data Analysis

“…To improve latency of interactions, downsampling the data has been proposed in various works target ting approximate query processing (AQP) (Chaudhuri, Ding, and Kan-Figure 1: Divergence of intent distribution: Single sampling strategy (stratified or uniform) for all the contexts in sequential data exploration can make user to get mislead into wrong analysis flow due to approximation errors. dula 2017; Park et al 2018;Sheoran et al 2022a) and visualizations (Park, Cafarella, and Mozafari 2016;Moritz et al 2017;Porwal et al 2022). For large datasets that are often a target for EDA (Galakatos et al 2017;Wang et al 2014), running queries on samples can substantially reduce the query latency.…”