让少量参数高效微调大模型,实现高精度与低内存兼顾
NeuroAda: Activating Each Neuron's Potential for Parameter-Efficient Fine-Tuning
- 选关键参数并加旁路,仅更新旁路参数
- 在23项任务上仅用0.02%参数就达顶尖效果
- 适合资源有限但需精细调优的场景
现有参数高效微调(PEFT)方法主要分为两类:添加模块型和选择性原位适应型。前者如LoRA引入额外模块,内存效率高,但表征能力受限;后者直接微调部分原始参数,适应更精确,但内存消耗大。为解决这一矛盾,我们提出NeuroAda,一种新型PEFT方法,在保持高内存效率的同时实现细粒度微调。该方法首先识别网络中重要连接,再为这些连接引入旁路结构,微调时仅更新旁路参数,冻结原始参数。在超过23项自然语言生成与理解任务上的实证表明,NeuroAda仅需≤0.02%可训练参数即可达到当前最优性能,同时降低高达60%的CUDA内存占用。代码已开源:https://github.com/FightingFighting/NeuroAda.git。
原文摘要 · Abstract (English)
Existing parameter-efficient fine-tuning (PEFT) methods primarily fall into two categories: addition-based and selective in-situ adaptation. The former, such as LoRA, introduce additional modules to adapt the model to downstream tasks, offering strong memory efficiency. However, their representational capacity is often limited, making them less suitable for fine-grained adaptation. In contrast, the latter directly fine-tunes a carefully chosen subset of the original model parameters, allowing for more precise and effective adaptation, but at the cost of significantly increased memory consumption. To reconcile this trade-off, we propose NeuroAda, a novel PEFT method that enables fine-grained model finetuning while maintaining high memory efficiency. Our approach first identifies important parameters (i.e., connections within the network) as in selective adaptation, and then introduces bypass connections for these selected parameters. During finetuning, only the bypass connections are updated, leaving the original model parameters frozen. Empirical results on 23+ tasks spanning both natural language generation and understanding demonstrate that NeuroAda achieves state-of-the-art performance with as little as $\leq \textbf{0.02}\%$ trainable parameters, while reducing CUDA memory usage by up to 60%. We release our code here: https://github.com/FightingFighting/NeuroAda.git.
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。