DSF-GAN: DownStream Feedback Generative Adversarial Network

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Perets, Oriel, Rappoport, Nadav
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913286134431744
author Perets, Oriel
Rappoport, Nadav
author_facet Perets, Oriel
Rappoport, Nadav
contents Utility and privacy are two crucial measurements of the quality of synthetic tabular data. While significant advancements have been made in privacy measures, generating synthetic samples with high utility remains challenging. To enhance the utility of synthetic samples, we propose a novel architecture called the DownStream Feedback Generative Adversarial Network (DSF-GAN). This approach incorporates feedback from a downstream prediction model during training to augment the generator's loss function with valuable information. Thus, DSF-GAN utilizes a downstream prediction task to enhance the utility of synthetic samples. To evaluate our method, we tested it using two popular datasets. Our experiments demonstrate improved model performance when training on synthetic samples generated by DSF-GAN, compared to those generated by the same GAN architecture without feedback. The evaluation was conducted on the same validation set comprising real samples. All code and datasets used in this research will be made openly available for ease of reproduction.
format Preprint
id arxiv_https___arxiv_org_abs_2403_18267
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DSF-GAN: DownStream Feedback Generative Adversarial Network
Perets, Oriel
Rappoport, Nadav
Machine Learning
Artificial Intelligence
I.2
Utility and privacy are two crucial measurements of the quality of synthetic tabular data. While significant advancements have been made in privacy measures, generating synthetic samples with high utility remains challenging. To enhance the utility of synthetic samples, we propose a novel architecture called the DownStream Feedback Generative Adversarial Network (DSF-GAN). This approach incorporates feedback from a downstream prediction model during training to augment the generator's loss function with valuable information. Thus, DSF-GAN utilizes a downstream prediction task to enhance the utility of synthetic samples. To evaluate our method, we tested it using two popular datasets. Our experiments demonstrate improved model performance when training on synthetic samples generated by DSF-GAN, compared to those generated by the same GAN architecture without feedback. The evaluation was conducted on the same validation set comprising real samples. All code and datasets used in this research will be made openly available for ease of reproduction.
title DSF-GAN: DownStream Feedback Generative Adversarial Network
topic Machine Learning
Artificial Intelligence
I.2
url https://arxiv.org/abs/2403.18267