Scholarlink

<p>In a world increasingly surrounded by data, data privacy and anonymization are becoming more and more important. Under these circumstances, the need for synthetic databases that replicate the characteristics of the population while preserving privacy is arising. In this article, we investigate how we can use Wasserstein Generative Adversarial Networks (WGANs), developed by Arjovsky et al. [<CitationRef CitationID="CR1">1</CitationRef>]&#xa0;in the context of image generation, to create synthetic survey databases. Survey data have both categorical and continuous variables and especially contain sampling weights that will be introduced in the proposed procedures. We evaluate the quality of the (generated) synthetic data through different indicators and especially a new practical and intuitive measure based on Support Vector Data Description (SVDD). All our analyses are achieved with the Labour Force Survey (LFS) data for Belgium.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Generating survey databases with Wasserstein Generative Adversarial Networks

  • 期刊论文

  • 发表日期：

    2025年11月11日

查看全文
  • Hugues Annoye,
  • Cédric Heuchenne

摘要

In a world increasingly surrounded by data, data privacy and anonymization are becoming more and more important. Under these circumstances, the need for synthetic databases that replicate the characteristics of the population while preserving privacy is arising. In this article, we investigate how we can use Wasserstein Generative Adversarial Networks (WGANs), developed by Arjovsky et al. [1] in the context of image generation, to create synthetic survey databases. Survey data have both categorical and continuous variables and especially contain sampling weights that will be introduced in the proposed procedures. We evaluate the quality of the (generated) synthetic data through different indicators and especially a new practical and intuitive measure based on Support Vector Data Description (SVDD). All our analyses are achieved with the Labour Force Survey (LFS) data for Belgium.