动态调整微调参数子集，用更少参数实现更好效果
Dynamic Subset Tuning: Expanding the Operational Range of Parameter-Efficient Training for Large Language Models
- 训练中动态选择要优化的参数子集，不固定位置
- 相同参数预算下，在多种任务上超越或媲美LoRA和提示调优
- 可灵活扩展参数比例，适配不同规模模型与任务
我们提出一种新的参数高效训练方法，通过优化现有模型中一小部分参数来适应下游任务。与以往方法不同，该参数子集的位置并非固定，而是随训练过程动态变化。这种动态选择机制可在更少参数下取得良好性能。该方法支持参数子集大小在任意比例范围内平滑扩展，而现有方法如提示调优和LoRA仅覆盖该范围的一小部分。在多种自然语言处理任务（机器翻译、问答、GSM8K、SuperGLUE）中，给定相同参数预算时，本方法在不同模型家族和规模下均达到或超过提示调优和LoRA的表现。
原文摘要 · Abstract (English)
We propose a novel parameter-efficient training (PET) method for large language models that adapts models to downstream tasks by optimizing a small subset of the existing model parameters. Unlike prior methods, this subset is not fixed in location but rather which parameters are modified evolves over the course of training. This dynamic parameter selection can yield good performance with many fewer parameters than extant methods. Our method enables a seamless scaling of the subset size across an arbitrary proportion of the total model size, while popular PET approaches like prompt tuning and LoRA cover only a small part of this spectrum. We match or outperform prompt tuning and LoRA in most cases on a variety of NLP tasks (MT, QA, GSM8K, SuperGLUE) for a given parameter budget across different model families and sizes.
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。