通过两阶段生成，让表格数据在采样时自动实现公平性，不牺牲质量。
FairDiffuseVQVAE: Sampling-Time Fairness in Tabular Diffusion via Conditional Refinement of Vector-Quantized Latents
- 先用向量量化自编码器重建数据，再用扩散模型条件精修以实现公平性。
- 在Adult等数据集上，公平性指标比现有方法提升47%~100%，同时误差极低。
- 适合需要高公平性且不希望损失数据质量的隐私共享与模型训练场景。
合成表格数据广泛应用于隐私保护数据共享、数据增强及缓解下游分类器偏见。当前顶尖的表格扩散模型（如TabDDPM、TabSyn）虽具备优异分布保真度，但缺乏公平性机制；而公平性感知生成器（DECAF、FairTGAN、FairTabDDPM）在训练中加入显式公平性惩罚，导致样本质量或下游效用显著下降。本文提出FairDiffuseVQVAE，一种两阶段架构：第一阶段为无公平性项的向量量化自编码器（含行级判别器），第二阶段采用类似DiffuseVAE的连续扩散精修器，基于保护属性与第一阶段重构结果进行无分类器引导。公平性作为采样分布的性质自然涌现——推理时对保护属性均匀采样即可构造性地实现人口均等。在Adult、Bank和COMPAS数据集上，FairDiffuseVQVAE达到最高平均人口均等比（0.702，较FairTabDDPM提升47%）和等化几率比（0.686，提升100%），同时保持最低平均成对相关误差（0.034），并明确以约15 AUC点为代价换取这些公平性收益。
原文摘要 · Abstract (English)
Synthetic tabular data is increasingly used in privacy-preserving data sharing, data augmentation, and to mitigate downstream classifier bias. State-of-the-art tabular diffusion models such as TabDDPM and TabSyn achieve excellent distributional fidelity but offer no mechanism for fairness; conversely, fairness-aware tabular generators (DECAF, FairTGAN, FairTabDDPM) impose explicit fairness penalties at training time, yielding modest fairness gains at substantial cost to either sample quality or downstream utility. We introduce FairDiffuseVQVAE, a two-stage architecture that decouples fidelity from fairness: a vector-quantized autoencoder with a row-level discriminator (Stage~1, no fairness terms) is followed by a DiffuseVAE-style continuous diffusion refiner that conditions on both the Stage-1 reconstruction and the protected attribute via classifier-free guidance (Stage~2). Fairness emerges as a property of the sampling distribution -- uniform sampling of the protected attribute at inference time enforces demographic parity by construction, rather than from competing loss terms. On the Adult, Bank and COMPAS datasets, FairDiffuseVQVAE achieves the highest mean Demographic Parity Ratio ($0.702$, $+47\%$ over FairTabDDPM) and Equalized Odds Ratio ($0.686$, $+100\%$). It also attains the lowest mean pair-wise correlation error ($0.034$) of any published method, while explicitly trading $\sim$$15$ AUC points for these fairness gains.
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。