In differentially private (DP) tabular data synthesis, the consensus is that statistical models are better than neural network (NN)-based methods. However, we argue that this conclusion is incomplete and overlooks the challenge of densely correlated datasets, where intricate dependencies can overwhelm statistical models. In such complex scenarios, neural networks are more suitable due to their capacity to fit complex distributions by learning directly from samples. Despite this potential, existing NN-based algorithms still suffer from significant limitations. We therefore propose MargNet, incorporating successful algorithmic designs of statistical models into neural networks. MargNet applies an adaptive marginal selection strategy and trains the neural networks to generate data that conforms to the selected marginals. On sparsely correlated datasets, our approach achieves utility close to the best statistical method while offering an average 7$\times$ speedup over it. More importantly, on densely correlated datasets, MargNet establishes a new state-of-the-art, reducing fidelity error by up to 26\% compared to the previous best. We release our code on GitHub.\footnote{https://github.com/KaiChen9909/margnet}

翻译：在差分隐私（DP）表格数据合成领域，学界普遍认为统计模型优于基于神经网络（NN）的方法。然而，我们认为这一结论并不完整，且忽视了密集关联数据集的挑战——其中复杂的依赖关系可能使统计模型不堪重负。在此类复杂场景中，神经网络因其能够直接从样本中学习以拟合复杂分布的特性而更为适用。尽管存在这种潜力，现有的基于神经网络的算法仍存在显著局限。为此，我们提出MargNet，将统计模型成功的算法设计融入神经网络中。MargNet采用自适应边际选择策略，并训练神经网络生成符合选定边际的数据。在稀疏关联数据集上，我们的方法实现了与最佳统计方法相近的效用，同时平均速度提升达7倍。更重要的是，在密集关联数据集上，MargNet确立了新的最优性能，相较于先前最佳方法，保真度误差降低高达26%。我们已在GitHub上开源代码。\\footnote{https://github.com/KaiChen9909/margnet}