Research Papers 论文研究 1d ago Updated 15h ago 更新于 15小时前 45

Flow Matching with Missing Data 带缺失数据的流匹配

Missing-Data Flow Matching treats missing coordinates as latent variables and averages the flow matching loss over possible completions, with the correction proven exact rather than approximate Under missing completely at random with true completions, the incomplete-data objective equals the complete-data objective, shifting all difficulty to the completion model Finite-sample analysis reveals counterintuitive results: missingness transfers rather than adds estimator variance, and a single compl 提出Missing-Data Flow Matching方法,将缺失坐标视为潜变量并对可能取值平均流匹配损失 证明在MCAR条件下不完整数据目标与完整数据目标精确相等,修正为精确而非近似 理论分析揭示缺失转移而非增加估计器方差,每个样本一个补全即可匹配完整数据方差 学习的补全模型引入的偏置由条件Wasserstein距离界定 实验验证确定性插补导致生成分布崩溃,方法在真实表格数据上表现优异

60
Hot 热度
72
Quality 质量
60
Impact 影响力

Analysis 深度分析

TL;DR

  • Missing-Data Flow Matching treats missing coordinates as latent variables and averages the flow matching loss over possible completions, with the correction proven exact rather than approximate
  • Under missing completely at random with true completions, the incomplete-data objective equals the complete-data objective, shifting all difficulty to the completion model
  • Finite-sample analysis reveals counterintuitive results: missingness transfers rather than adds estimator variance, and a single completion per example already matches complete-data variance exactly
  • A learned completion model introduces a single irreducible bias bounded by its expected conditional Wasserstein distance to the true completion law
  • Experiments validate theory and show deterministic (rather than frozen) imputation is what collapses the generated distribution

Why It Matters

This work bridges a critical gap between flow matching theory and real-world practice, where missing data is the norm rather than the exception. By proving that the proposed correction is exact and providing finite-sample guarantees, it gives practitioners a theoretically sound foundation for training generative models on incomplete datasets without resorting to ad-hoc imputation strategies.

Technical Details

  • The method formulates Missing-Data Flow Matching by treating missing coordinates as latent variables and averaging the flow matching loss over their possible values, with a proof that the correction is exact under missing completely at random (MCAR) with true completions
  • Finite-sample analysis demonstrates that missingness transfers estimator variance rather than adding it, and that one completion per example achieves complete-data variance exactly, making it optimal under a fixed evaluation budget
  • The irreducible bias from a learned completion model is bounded by the expected conditional Wasserstein distance between the learned completion distribution and the true completion law
  • Experiments on real tabular data compare against strong classical and deep imputation baselines, with key findings that deterministic imputation collapses the generated distribution while learned (non-frozen) imputation preserves it

Industry Insight

  • Practitioners working with real-world tabular data should avoid deterministic imputation pipelines when combining with flow matching, as they provably collapse distributional fidelity; learned, non-frozen completion models are essential
  • The theoretical result that one completion suffices under a fixed budget can significantly reduce computational costs in training, challenging the intuition that multiple imputations are necessary
  • As missing data is pervasive in healthcare, finance, and scientific domains, this framework provides a principled path toward deploying flow-based generative models in production settings where data completeness cannot be guaranteed

TL;DR

  • 提出Missing-Data Flow Matching方法,将缺失坐标视为潜变量并对可能取值平均流匹配损失
  • 证明在MCAR条件下不完整数据目标与完整数据目标精确相等,修正为精确而非近似
  • 理论分析揭示缺失转移而非增加估计器方差,每个样本一个补全即可匹配完整数据方差
  • 学习的补全模型引入的偏置由条件Wasserstein距离界定
  • 实验验证确定性插补导致生成分布崩溃,方法在真实表格数据上表现优异

为什么值得看

流匹配作为新兴生成建模范式,其假设完全可观测数据的局限性在现实场景中极为突出。本文提供了首个具有精确理论保证的缺失数据处理框架,对推动生成模型在真实世界数据上的应用具有重要价值。

技术解析

  • 核心方法:将缺失坐标建模为潜变量,通过对所有可能取值进行平均来构建流匹配损失函数,而非简单插补后训练。
  • 理论保证:在MCAR(完全随机缺失)且使用真实补全的条件下,不完整数据目标与完整数据目标精确相等,缺失本身不改变流匹配的学习目标。
  • 方差分析:缺失转移而非增加估计器方差;每个样本一个补全已精确匹配完整数据方差;在固定评估预算下,一个补全即为最优。
  • 偏置界定:学习的补全模型引入单一不可约偏置,其上界由补全模型与真实补全分布之间的条件Wasserstein距离界定。
  • 实验发现:确定性插补而非冻结插补是导致生成分布崩溃的根本原因;在真实表格数据上与经典和深度插补基线进行了对比验证。

行业启示

  • 流匹配等生成模型在医疗、金融等数据缺失普遍的场景中落地时,需将补全质量视为核心瓶颈而非辅助环节。
  • 补全策略应优先采用随机而非确定性方法,以避免生成分布退化;补全模型的质量直接决定最终生成效果。
  • 理论分析表明无需大量补全样本即可达到最优性能,降低了实际部署的计算成本与复杂度。

Disclaimer: The above content is generated by AI and is for reference only. 免责声明:以上内容由 AI 生成,仅供参考。

Research 科学研究 Training 训练 Dataset 数据集