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

43 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: "数据回放 (Data Replay)"
created: 2026-05-21
type: concept
tags: ["continual-learning", "knowledge-retention", "catastrophic-forgetting"]
sources: ["[[when-large-multimodal-models-confront-evolving-knowledge]]"]
---
# 数据回放 (Data Replay)
## 定义
数据回放是缓解[[capability-degradation|能力退化]]的一种**直接排练策略**,通过将**旧预训练数据**与新注入数据混合进行微调,强制模型"复习旧知"。
## 实现
在 MMEVOKE 论文中:
- Replay + Full-FT随机抽样 10%MMEVOKE 数据量大小)的旧预训练数据,与新注入数据混合,使用 Full-FT
- Replay + LoRA同上使用 LoRA 策略
## 效果LLaVA-v1.5
- Replay + Full-FT缓解退化**排名第 3**
- Replay + LoRA**排名第 1**,在 MMMU 和 MathVision 上超过 Vanilla 分别 +1.75% 和 +2.20%
## 机制
通过重新暴露于旧数据,**重新激活旧知识网络**,防止新知识覆盖已有参数。
## 与 MoELoRA 的比较
| 策略 | Replay | MoELoRA |
|------|--------|---------|
| 机制 | 直接排练旧数据 | 结构性隔离新知识 |
| 优势 | 效果最佳 | 无需存储旧数据 |
| 劣势 | 需要旧数据存储 | 需修改模型架构 |
## 参见
- [[moe-lora|MoELoRA]]
- [[knowledge-retention|知识保留]]
- [[continual-learning|持续学习]]