20260601
This commit is contained in:
37
concepts/data-label-consistency.md
Normal file
37
concepts/data-label-consistency.md
Normal file
@@ -0,0 +1,37 @@
|
||||
---
|
||||
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
|
||||
Reference in New Issue
Block a user