Generating synthetic data through generative models is gaining interest in the ML community and beyond, promising a future where datasets can be tailored to individual needs. Unfortunately, synthetic data is usually not perfect, resulting in potential errors in downstream tasks. In this work we explore how the generative process affects the downstream ML task. We show that the naive synthetic data approach -- using synthetic data as if it is real -- leads to downstream models and analyses that do not generalize well to real data. As a first step towards better ML in the synthetic data regime, we introduce Deep Generative Ensemble (DGE) -- a framework inspired by Deep Ensembles that aims to implicitly approximate the posterior distribution over the generative process model parameters. DGE improves downstream model training, evaluation, and uncertainty quantification, vastly outperforming the naive approach on average. The largest improvements are achieved for minority classes and low-density regions of the original data, for which the generative uncertainty is largest.
Synthetic Acute Hypotension and Sepsis Datasets Based on MIMIC-III and Published as Part of the Health Gym Project
University of New South Wales(新南威尔士大学);Australian National University(澳大利亚国立大学);The George Institute for Global Health(乔治全球健康研究院);Imperial College London(伦敦帝国理工学院)
Synthetic data generation for a longitudinal cohort study -- Evaluation, method extension and reproduction of published data analysis results
ZB MED – Information Centre for Life Sciences(ZB MED——生命科学信息中心);Bielefeld University(比勒费尔德大学);University of Bonn(波恩大学);Fraunhofer Institute for Algorithms and Scientific Computing SCAI(弗劳恩霍夫算法与科学计算研究所(SCAI));Berlin Institute of Health at Charité – Universitätsmedizin Berlin(柏林夏里特医学院柏林卫生研究所)
Using Synthetic Data to estimate the True Error is theoretically and practically doable
Hanoi University of Science and Technology(河内理工大学);Thai Nguyen University of Economics and Business Administration(Thai Nguyen经济与商业管理大学);Vietnam Posts and Telecommunications Group(越南邮电集团)
When Does Synthetic Data Augmentation Improve Score-Based Imbalanced Classification?
Department of Electrical & Computer Engineering, Duke University(电气与计算机工程系,杜克大学);Department of Biostatistics & Bioinformatics, Duke University(生物统计学与生物信息学系,杜克大学);Department of Biostatistics & Bioinformatics and Department of Computer Science, Duke University(生物统计学与生物信息学系和计算机科学系,杜克大学)
When Privacy Isn't Synthetic: Hidden Data Leakage in Generative AI Models
Department of Mathematical Sciences University of Texas at El Paso(数学科学系德克萨斯理工大学埃尔帕索分校);Department of Computer Science University of Texas at El Paso(计算机科学系德克萨斯理工大学埃尔帕索分校);Department of Radiology St. Jude Children’s Research Hospital(放射医学系圣犹太儿童研究医院)
Critical Challenges and Guidelines in Evaluating Synthetic Tabular Data: A Systematic Review
Healthy Lifespan Institute, School of Computer Science, University of Sheffield(健康寿命研究所,计算机科学学院,谢菲尔德大学);School of Electrical and Electronic Engineering, University of Sheffield(电子与电气工程学院,谢菲尔德大学);Healthy Lifespan Institute, School of Sociological Studies, Politics and International Relations, University of Sheffield(健康寿命研究所,社会科学学院,政治与国际关系,谢菲尔德大学);Digital Environment Research Institute, Queen Mary University of London(数字环境研究 institutes,伦敦女王大学)
Amsterdam University Medical Center, University of Amsterdam(阿姆斯特丹大学阿姆斯特丹大学医学中心);University Medical Center Utrecht(乌得勒支大学医学中心);Image Sciences Institute(图像科学研究所)