20260601
This commit is contained in:
42
concepts/null-space-projection-knowledge.md
Normal file
42
concepts/null-space-projection-knowledge.md
Normal file
@@ -0,0 +1,42 @@
|
||||
---
|
||||
title: "零空间投影知识保留 (Null Space Projection for Knowledge Retention)"
|
||||
created: 2026-05-21
|
||||
type: concept
|
||||
tags: ["null-space", "continual-learning", "linear-algebra"]
|
||||
sources: ["[[kore-knowledge-injection]]"]
|
||||
---
|
||||
|
||||
# 零空间投影知识保留
|
||||
|
||||
## 定义
|
||||
|
||||
零空间投影知识保留是 [[kore-constraint|KORE-CONSTRAINT]] 的核心技术,通过将微调方向限制在已有知识协方差矩阵的**零空间**中,实现新知识注入与旧知识保留的完美解耦。
|
||||
|
||||
## 数学原理
|
||||
|
||||
给定预训练权重 W₀ 和激活协方差矩阵 C = XX^T:
|
||||
|
||||
目标:W*C ≈ W₀C(旧知识的输出保持稳定)
|
||||
|
||||
→ (W₀ + BA)C ≈ W₀C → BAC ≈ 0 → **AC = 0**
|
||||
|
||||
解决方案:将 A 矩阵限制在 C 的零空间中:
|
||||
1. SVD(C) → 提取零空间的基向量 Û
|
||||
2. P = ÛÛ^T(零空间投影矩阵)
|
||||
3. W₀P 作为微调的起点
|
||||
|
||||
## 优势
|
||||
|
||||
- **精确性**:数学上保证 BAC = 0,而非启发式近似
|
||||
- **可组合性**:支持多批知识的顺序注入
|
||||
- **参数效率**:与 LoRA 无缝集成,增量参数极少
|
||||
|
||||
## 直观理解
|
||||
|
||||
协方差矩阵 C 的**列空间**是已有知识占据的"空间"。零空间是与之正交的"未使用空间"。在零空间中微调意味着:新知识被写入模型的"空白区域",不会覆盖已有知识。
|
||||
|
||||
## 参见
|
||||
|
||||
- [[kore-constraint|KORE-CONSTRAINT]]
|
||||
- [[covariance-matrix-knowledge|协方差矩阵知识存储]]
|
||||
- [[null-space|零空间]]
|
||||
Reference in New Issue
Block a user