Files
myWiki/concepts/parameter-efficient-training.md

46 lines
1.5 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: "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
- 200500× 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]]