不训练即可解决多模型融合中的知识冲突问题
CAT Merging: A Training-Free Approach for Resolving Conflicts in Model Merging
- 通过选择性裁剪任务向量中的冲突成分实现无训练融合
- 在视觉、语言任务上平均提升2.5%（ViT-B/32）和2.0%（ViT-L/14）
- 适合需要快速集成多个专家模型的场景
多任务模型融合为在无需额外训练的情况下将多个专家模型整合成统一模型提供了有前景的范式。现有最先进方法如任务算术及其变体，通过累加任务向量——即预训练与微调模型之间的参数差异——来实现融合。然而，任务向量累加常受知识冲突阻碍，导致性能下降。为此，我们提出冲突感知任务融合（CAT Merging），一种新型无训练框架，可选择性地裁剪任务向量中易引发冲突的组件。CAT Merging引入多种参数特定策略，包括线性权重的投影，以及归一化层中缩放和偏移参数的掩码。在视觉、语言及视觉-语言任务上的大量实验表明，CAT Merging有效抑制了知识冲突，在状态领先方法基础上实现最高2.5%（ViT-B/32）和2.0%（ViT-L/14）的平均准确率提升。
原文摘要 · Abstract (English)
Multi-task model merging offers a promising paradigm for integrating multiple expert models into a unified model without additional training. Existing state-of-the-art techniques, such as Task Arithmetic and its variants, merge models by accumulating task vectors -- the parameter differences between pretrained and finetuned models. However, task vector accumulation is often hindered by knowledge conflicts, leading to performance degradation. To address this challenge, we propose Conflict-Aware Task Merging (CAT Merging), a novel training-free framework that selectively trims conflict-prone components from the task vectors. CAT Merging introduces several parameter-specific strategies, including projection for linear weights and masking for scaling and shifting parameters in normalization layers. Extensive experiments on vision, language, and vision-language tasks demonstrate that CAT Merging effectively suppresses knowledge conflicts, achieving average accuracy improvements of up to 2.5% (ViT-B/32) and 2.0% (ViT-L/14) over state-of-the-art methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。