arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.10774cs.AIcs.CL
收藏

Flexora:面向大型语言模型的灵活低秩适配

Flexora: Flexible Low Rank Adaptation for Large Language Models

College of Computer Science and Software Engineering, Shenzhen University(深圳大学计算机科学与软件工程学院);Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ)(广东人工智能与数字经济实验室);Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州));School of Information Technology, Carleton University(卡尔顿大学信息科技学院)

Chenxing Wei, Yao Shu, Ying Tiffany He, Fei Richard Yu

AI总结:

针对LoRA在特定任务上过拟合的问题,提出Flexora方法,通过超参数优化和展开微分自动选择关键层进行微调,在多个预训练模型和自然语言任务上持续优于现有基线。

摘要:

大型语言模型(LLMs)通过增加模型参数的规模推动了人工智能的进步,这显著增强了泛化能力,并在实践中解锁了新的能力。然而,它们在特定下游任务上的性能通常受到其在这些任务上的知识边界的阻碍。因此,微调技术,特别是广泛使用的低秩适配(LoRA)方法,已被引入以扩展这些任务上的边界,而LoRA在某些任务上可能因其潜在的过拟合而表现不佳。为了克服这种过拟合并提升LoRA的性能,我们提出了灵活低秩适配(Flexora)方法,以自动且灵活地选择需要微调的最重要层,从而在不同下游任务上实现最佳性能。具体而言,Flexora首先将这一层选择问题构建为一个定义良好的超参数优化(HPO)问题,然后使用展开微分(UD)方法来解决该问题,最后基于优化后的超参数选择最有用的层。我们在许多预训练模型和自然语言任务上的广泛实验表明,Flexora能够持续优于现有基线,这表明了我们的Flexora在实践中的有效性。此外,我们提供了有洞察力的理论结果和许多消融研究,以全面理解我们的Flexora。

英文摘要:

Large Language Models (LLMs) are driving advancements in artificial intelligence by increasing the scale of model parameters, which has significantly enhanced generalization ability and unlocked new capabilities in practice. However, their performance in specific downstream tasks is usually hindered by their knowledge boundaries on these tasks. Thus, fine-tuning techniques, especially the widely used Low-Rank Adaptation (LoRA) method, have been introduced to expand the boundaries on these tasks, whereas LoRA would underperform on certain tasks owing to its potential overfitting on these tasks. To overcome this overfitting and improve the performance of LoRA, we propose the flexible low rank adaptation (Flexora) method to automatically and flexibly select the most important layers needing to be fine-tuned to achieve the best performance on different downstream tasks. Specifically, Flexora firstly frames this layer selection problem as a well-defined hyperparameter optimization (HPO) problem, then addresses it using the unrolled differentiation (UD) method, and finally selects the most useful layers based on the optimized hyperparameters. Our extensive experiments on many pretrained models and natural language tasks show that Flexora is able to consistently improve over the existing baselines, indicating the effectiveness of our Flexora in practice. We additionally provide insightful theoretical results and many ablation studies to deliver a comprehensive understanding of our Flexora.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑