arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2407.01643cs.LGcs.CY
收藏

一种用于家庭与个体联合人口合成的深度生成框架

A Deep Generative Framework for Joint Households and Individuals Population Synthesis

University of Delaware(特拉华大学)

Xiao Qian, Utkarsh Gangwal, Shangjia Dong, Rachel Davidson

AI总结:

本文提出基于VAE的深度生成框架,通过关系数据结构、预训练—微调迁移学习和D-BCE损失,联合生成符合普查片区边际分布并保留家庭与个体关联的合成人口。

摘要:

家庭和个体层面的社会人口数据对于理解人类与基础设施互动及政策制定至关重要。然而,Public Use Microdata Sample(PUMS,公共使用微数据样本)仅提供州级样本,而人口普查片区数据仅提供变量的边际分布,不包含变量间相关性。因此,我们需要一个准确的合成人口数据集,既能保持微数据中观察到的一致变量相关性,又能保留家庭—个体以及个体—个体关系,遵循州级统计数据,并准确表示人口的地理分布。我们提出一种利用 variational autoencoder(VAE,变分自编码器)的深度生成框架,以生成具备上述特征的合成人口。方法贡献包括:(1)一种用于捕捉家庭—个体和个体—个体关系的新数据结构;(2)包含预训练和微调步骤的迁移学习过程,用于生成其聚合分布与人口普查片区边际分布一致的家庭和个体;(3)解耦二元交叉熵(D-BCE)损失函数,支持分布偏移和样本外记录生成。在美国特拉华州的应用模型结果表明,与现有方法相比,该框架能够确保生成的家庭—个体记录的真实性,并准确描述人口普查片区层面的人口统计数据。此外,在美国北卡罗来纳州的测试取得了有前景的结果,支持了本方法的可迁移性。

英文摘要:

Household and individual-level sociodemographic data are essential for understanding human-infrastructure interaction and policymaking. However, the Public Use Microdata Sample (PUMS) offers only a sample at the state level, while census tract data only provides the marginal distributions of variables without correlations. Therefore, we need an accurate synthetic population dataset that maintains consistent variable correlations observed in microdata, preserves household-individual and individual-individual relationships, adheres to state-level statistics, and accurately represents the geographic distribution of the population. We propose a deep generative framework leveraging the variational autoencoder (VAE) to generate a synthetic population with the aforementioned features. The methodological contributions include (1) a new data structure for capturing household-individual and individual-individual relationships, (2) a transfer learning process with pre-training and fine-tuning steps to generate households and individuals whose aggregated distributions align with the census tract marginal distribution, and (3) decoupled binary cross-entropy (D-BCE) loss function enabling distribution shift and out-of-sample records generation. Model results for an application in Delaware, USA demonstrate the ability to ensure the realism of generated household-individual records and accurately describe population statistics at the census tract level compared to existing methods. Furthermore, testing in North Carolina, USA yielded promising results, supporting the transferability of our method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑