用SVD对齐LoRA模型权重，提升多任务合并效果
Model merging with SVD to tie the Knots
- 通过SVD将不同LoRA模型权重映射到对齐空间
- 在视觉与语言任务上合并性能提升最高4.3%
- 新基准评估合并模型的通用性，适合多任务研究者
近期模型合并方法表明，可将针对不同任务微调的全参数模型参数融合为一个无需重新训练即可解决所有任务的模型。然而，该方法在合并LoRA微调模型时表现不佳。我们研究发现，与全参数微调模型相比，LoRA微调模型的权重对齐度更低。为此，我们提出KnOTS，利用SVD将多个LoRA模型权重联合变换至对齐空间，使现有合并方法更有效。此外，我们构建了一个新基准，专门评估合并后模型是否具备通用性。实验显示，KnOTS在多个视觉与语言基准上，包括新设定下，性能提升最高达4.3%。代码已开源：https://github.com/gstoica27/KnOTS。
原文摘要 · Abstract (English)
Recent model merging methods demonstrate that the parameters of fully-finetuned models specializing in distinct tasks can be combined into one model capable of solving all tasks without retraining. Yet, this success does not transfer well when merging LoRA finetuned models. We study this phenomenon and observe that the weights of LoRA finetuned models showcase a lower degree of alignment compared to their fully-finetuned counterparts. We hypothesize that improving this alignment is key to obtaining better LoRA model merges, and propose KnOTS to address this problem. KnOTS uses the SVD to jointly transform the weights of different LoRA models into an aligned space, where existing merging methods can be applied. In addition, we introduce a new benchmark that explicitly evaluates whether merged models are general models. Notably, KnOTS consistently improves LoRA merging by up to 4.3% across several vision and language benchmarks, including our new setting. We release our code at: https://github.com/gstoica27/KnOTS.
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。