根据数据质量和层敏感性动态调整微调，提升效率与效果
TsqLoRA: Towards Sensitivity and Quality Low-Rank Adaptation for Efficient Fine-Tuning
- 按数据质量选样本，按层敏感度分配低秩参数
- 在多个NLP任务上实现更高性能，参数量减少60%以上
- 适合资源受限场景下的高效模型微调
在自然语言处理中，微调大预训练模型已成为主流方法。全参数微调计算开销大、内存占用高，尤其在资源受限环境下。现有参数高效微调方法虽减少了可训练参数，但通常忽略不同模型层对参数更新的敏感差异以及训练数据的重要性。本文提出TsqLoRA，一种融合数据质量驱动选择与敏感性感知的低秩适配方法，包含两个核心组件：质量感知采样机制，用于选择最具信息量的训练数据；动态秩分配模块，根据各层敏感度自适应调整其低秩秩数。实验表明，TsqLoRA在多种NLP任务上提升了微调效率，同时保持甚至超越原有性能。代码将公开于https://github.com/Benjamin-Ricky/TsqLoRA。
原文摘要 · Abstract (English)
Fine-tuning large pre-trained models for downstream tasks has become a fundamental approach in natural language processing. Fully fine-tuning all model parameters is computationally expensive and memory-intensive, especially in resource-constrained environments. Existing parameter-efficient fine-tuning methods reduce the number of trainable parameters but typically overlook the varying sensitivity of different model layers and the importance of training data. In this work, we propose TsqLoRA, a novel method that integrates data-quality-driven selection with sensitivity-aware low-rank adaptation, consisted of two main components: a quality-aware sampling mechanism for selecting the most informative training data, and a dynamic rank allocation module that adjusts the rank of each layer based on its sensitivity to parameter updates. The experimental results demonstrate that TsqLoRA improves fine-tuning efficiency while maintaining or even improving performance on a variety of NLP tasks. Our code will be available at https://github.com/Benjamin-Ricky/TsqLoRA.
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。