20260706:新增一些文章
This commit is contained in:
45
concepts/parameter-efficient-training.md
Normal file
45
concepts/parameter-efficient-training.md
Normal file
@@ -0,0 +1,45 @@
|
||||
---
|
||||
title: "Parameter-Efficient Training: 参数高效训练"
|
||||
created: 2026-06-25
|
||||
updated: 2026-06-25
|
||||
type: concept
|
||||
tags: [efficient-training, model-compression, meta-learning]
|
||||
sources: ["[[sen-mapping-networks]]"]
|
||||
---
|
||||
|
||||
# Parameter-Efficient Training (参数高效训练)
|
||||
|
||||
Parameter-Efficient Training 指在不显著损失模型性能的前提下,大幅减少**可训练参数量**的方法论。
|
||||
|
||||
## 主要策略分类
|
||||
|
||||
### 1. 内部缩减(训练目标网络本身)
|
||||
|
||||
- **Pruning**:训练中或训练后稀疏化([[lottery-ticket-hypothesis|Lottery Ticket]])
|
||||
- **Quantization-Aware Training (QAT)**:低精度训练
|
||||
- **Low-Rank 约束**:W ≈ UV^T,训练 U, V 而非 W
|
||||
|
||||
### 2. 外部缩减(不训练目标网络)
|
||||
|
||||
- **[[hypernetworks|HyperNetworks]]**:另一个网络生成权重(但仍需训练目标网络)
|
||||
- **[[sen-mapping-networks|Mapping Networks]]**:仅训练隐向量,目标网络不训练 ← 最激进的外部缩减
|
||||
- **预测参数**:从少量给定权重预测其余权重
|
||||
|
||||
### 3. 混合策略
|
||||
|
||||
Mapping Networks + LRD(低秩分解 FC 层)+ Pruning,同时减少训练和推理参数。
|
||||
|
||||
## Mapping Networks 的定位
|
||||
|
||||
在图 1 的分类框架中,Mapping Networks 处于**理想位置**:
|
||||
|
||||
- **训练聚焦**(而非仅推理聚焦)
|
||||
- **外部缩减**(不训练目标网络)
|
||||
- **利用流形结构**(Weight-Manifold Hypothesis)
|
||||
- 200–500× 可训练参数缩减,500× 参数效率(99.5% 缩减)
|
||||
|
||||
## 参考
|
||||
|
||||
- [[low-rank-decomposition]]
|
||||
- [[weight-modulation]]
|
||||
- [[mapping-theorem]]
|
||||
Reference in New Issue
Block a user