Files
myWiki/concepts/data-label-consistency.md
2026-06-01 10:46:01 +08:00

38 lines
1.3 KiB
Markdown
Raw Blame History

This file contains ambiguous Unicode characters

This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

---
title: "Data-Label Consistency (数据-标签一致性)"
created: 2026-05-26
type: concept
tags: ["time-series", "data-augmentation", "forecasting"]
sources: ["temporal-patch-shuffle-tps"]
---
# Data-Label Consistency
> 时间序列预测增强的必要条件:输入 x 与目标 y 必须被联合变换,以保持序列的时间连续性。
## 定义
记 look-back 窗口为 x预测目标为 y。训练作用的对象是连续序列 s = x ∥ y增强应作用在拼接后的序列上
```
s = x ∥ y
s̃ = 𝒜(s)
(x̃, ỹ) = Split(s̃)
```
## 为什么重要
- 只对 x 增强、让 y 原封不动 → 输入与目标之间的天然连续性被人为切断
- 在 [[temporal-patch-shuffle|TPS]] 的消融实验中,**数据-标签一致性的破坏是单一消融中性能下降最大的因素**
- 这是预测增强区别于分类增强的根本约束
## 实践含义
所有有效的预测增强方法([[freqmask-freqmix|FreqMask/FreqMix]]、[[wavemask-wavemix|WaveMask/WaveMix]]、[[temporal-patch-shuffle|TPS]])都采用了这个拼接-增强-拆分范式。
## 相关页面
- [[time-series-forecasting-augmentation]] — 预测增强框架
- [[temporal-patch-shuffle]] — 内置数据-标签一致性的 SOTA 方法
- [[forecasting-augmentation-taxonomy]] — 各类方法对此原则的遵守情况