ReStore -- Neural Data Completion for Relational Databases

TL;DR

ReStore introduces neural schema-structured models to automatically complete incomplete relational databases, significantly improving the accuracy of aggregate query results compared to using incomplete data.

Contribution

The paper presents ReStore, a novel neural data completion method for relational databases that automates missing data synthesis to enhance query accuracy.

Findings

Reduces relative error of aggregate queries by up to 390%.

Outperforms traditional incomplete data query results.

Demonstrates effectiveness on real-world datasets.

Abstract

Classical approaches for OLAP assume that the data of all tables is complete. However, in case of incomplete tables with missing tuples, classical approaches fail since the result of a SQL aggregate query might significantly differ from the results computed on the full dataset. Today, the only way to deal with missing data is to manually complete the dataset which causes not only high efforts but also requires good statistical skills to determine when a dataset is actually complete. In this paper, we propose an automated approach for relational data completion called ReStore using a new class of (neural) schema-structured completion models that are able to synthesize data which resembles the missing tuples. As we show in our evaluation, this efficiently helps to reduce the relative error of aggregate queries by up to 390% on real-world data compared to using the incomplete data directly for query answering.