---
id: 20260804-T0-10
title: "缺失数据处理新方法：Flow Matching 扩展至不完整数据集"
title_en: "New Missing-Data Flow Matching Method Handles Incomplete Datasets"
url: https://ai.daily.yangsir.net/daily/20260804-T0-10
issue_date: 2026-08-04
publish_date: 2026-08-03T04:00:00.000Z
category: research
source_name: "arXiv cs.LG (ML)"
source_url: https://arxiv.org/abs/2607.28698
---

# 缺失数据处理新方法：Flow Matching 扩展至不完整数据集

arXiv 新论文提出缺失数据流匹配（Missing-Data Flow Matching）。该方法将训练样本中的缺失坐标视为潜在变量，并对流匹配损失进行平均化处理，从而扩展了传统流匹配模型仅能处理完全观测数据的限制，适用于医疗记录等现实世界中的不完整数据集。

## English Version

**New Missing-Data Flow Matching Method Handles Incomplete Datasets**

A new arXiv paper introduces Missing-Data Flow Matching, which treats missing coordinates in training samples as latent variables and averages the flow matching loss. This extends standard flow matching beyond fully observed data, making it applicable to incomplete real-world datasets like medical records.

---

**来源**：[arXiv cs.LG (ML)](https://arxiv.org/abs/2607.28698)

**详情页**：https://ai.daily.yangsir.net/daily/20260804-T0-10

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*