用全连接网络从高维噪声生成真实数据，速度快且隐私保护好。
Synthesizing real-world distributions from high-dimensional Gaussian Noise with Fully Connected Neural Network
- 用全连接网络将高维高斯噪声映射到真实数据分布。
- 在25个数据集上比现有方法快数个数量级，MMD得分接近顶尖水平。
- 结合PCA与随机损失函数，兼顾数据相似性与隐私保护。
合成数据在机器学习应用与研究中具有诸多优势，如通过数据增强提升性能、保护原始样本隐私。本文提出一种基于全连接神经网络的高效合成数据生成方法，将高维随机高斯分布转换为逼近目标真实数据集的分布。该方法结合专为表格数据设计的预处理、分布建模与主成分分析（PCA）降维，进一步提升隐私保护效果。提出两种基于Wasserstein距离与特征协方差的随机化损失函数，以及一种随机成对误差减少损失函数。在25个多样化的真实世界表格数据集上的实验表明，该方法在分布相似性与隐私保护评分上优于当前主流生成方法，并在参考MMD得分上实现现代深度学习方案数个数量级的速度提升。实验还评估了合成数据在分类任务中的分布相似性、隐私保护能力与可用性。
原文摘要 · Abstract (English)
The use of synthetic data in machine learning applications and research offers many benefits, including performance improvements through data augmentation and privacy preservation of original samples. This work proposes an efficient synthetic data generation method based on a fully connected neural network that transforms a high-dimensional random Gaussian distribution to approximate a target real-world dataset. The proposed solution combines data preprocessing designed for tabular data with distribution modeling and PCA dimensionality reduction to further enhance data privacy. The work also defines two dedicated randomized loss functions based on Wasserstein distance combined with feature Covariance and a randomized pairwise error reduction loss function. The experiments conducted on 25 diverse tabular real-world datasets confirm that the proposed solution obtains similarity and privacy scores relative to the state-of-the-art generative methods and achieves reference MMD scores orders of magnitude faster than modern deep learning solutions. The experiments involved analyzing distributional similarity, privacy protection, and the utility of synthetic data in classification tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。