GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916098890268672 |
|---|---|
| author | Fallahian, Mohammadali Dorodchi, Mohsen Kreth, Kyle |
| author_facet | Fallahian, Mohammadali Dorodchi, Mohsen Kreth, Kyle |
| contents | In data-driven systems, data exploration is imperative for making real-time decisions. However, big data is stored in massive databases that are difficult to retrieve. Approximate Query Processing (AQP) is a technique for providing approximate answers to aggregate queries based on a summary of the data (synopsis) that closely replicates the behavior of the actual data, which can be useful where an approximate answer to the queries would be acceptable in a fraction of the real execution time. This study explores the novel utilization of Generative Adversarial Networks (GANs) in the generation of tabular data that can be employed in AQP for synopsis construction. We thoroughly investigate the unique challenges posed by the synopsis construction process, including maintaining data distribution characteristics, handling bounded continuous and categorical data, and preserving semantic relationships and then introduce the advancement of tabular GAN architectures that overcome these challenges. Furthermore, we propose and validate a suite of statistical metrics tailored for assessing the reliability of the GAN-generated synopses. Our findings demonstrate that advanced GAN variations exhibit a promising capacity to generate high-fidelity synopses, potentially transforming the efficiency and effectiveness of AQP in data-driven systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2212_09015 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions Fallahian, Mohammadali Dorodchi, Mohsen Kreth, Kyle Databases Machine Learning In data-driven systems, data exploration is imperative for making real-time decisions. However, big data is stored in massive databases that are difficult to retrieve. Approximate Query Processing (AQP) is a technique for providing approximate answers to aggregate queries based on a summary of the data (synopsis) that closely replicates the behavior of the actual data, which can be useful where an approximate answer to the queries would be acceptable in a fraction of the real execution time. This study explores the novel utilization of Generative Adversarial Networks (GANs) in the generation of tabular data that can be employed in AQP for synopsis construction. We thoroughly investigate the unique challenges posed by the synopsis construction process, including maintaining data distribution characteristics, handling bounded continuous and categorical data, and preserving semantic relationships and then introduce the advancement of tabular GAN architectures that overcome these challenges. Furthermore, we propose and validate a suite of statistical metrics tailored for assessing the reliability of the GAN-generated synopses. Our findings demonstrate that advanced GAN variations exhibit a promising capacity to generate high-fidelity synopses, potentially transforming the efficiency and effectiveness of AQP in data-driven systems. |
| title | GAN-based Tabular Data Generator for Constructing Synopsis in Approximate Query Processing: Challenges and Solutions |
| topic | Databases Machine Learning |
| url | https://arxiv.org/abs/2212.09015 |