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 2409.18860cs.CV
收藏

LW2G:为基于提示的持续学习学习是否增长

LW2G: Learning Whether to Grow for Prompt-based Continual Learning

College of Computer Science and Technology, Zhejiang University, China(浙江大学计算机科学与技术学院);State Key Laboratory for Novel Software Technology, Nanjing University, China(南京大学新型软件技术国家重点实验室);Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi(阿布扎赫德莫伊丁·本·扎耶德人工智能大学);Huawei Zurich Research Center, Switzerland(华为苏黎世研究中心)

Qian Feng, Da-wei Zhou, Hanbin Zhao, Chao Zhang, Jiahua Dong, Dengxin Dai, Hui Qian

AI总结:

本文提出插件方法LW2G,利用任务间差异形成高效提示集池,通过HFC度量和动态阈值自适应决定是否增长,实现任务内知识共享并避免提示池成本无限增加。

摘要:

最近的基于提示的持续学习(PCL)在预训练模型上取得了显著性能。这些方法通过在学习时添加新提示集来扩展提示池,并在推理时选择正确的集。先前的研究表明,单独学习任务级提示集和较低的选择准确性对PCL的性能构成了挑战。在本文中,我们提出了一种插件方法,学习是否增长(LW2G),该方法利用任务间的差异来形成有效且高效的提示集池,从而实现任务内知识共享与协作,并避免提示池成本的无限增加。具体而言,当若干任务共享某些共性时使用共享集,而当新任务与先前任务存在显著差异时添加新集。为此,我们开发了一种称为阻碍前向能力(HFC)的度量,通过将原始梯度修改至旧特征空间的正交补上来测量对学习新任务造成的阻碍。借助HFC,一种自动化方案——动态增长方法——通过动态阈值自适应地学习是否增长。此外,我们设计了基于梯度的约束,以确保更新提示与预训练知识之间的一致性。大量实验表明了我们方法的有效性。代码可在 https://github.com/RAIAN08/LW2G 获取。

英文摘要:

Recent Prompt-based Continual learning (PCL) has achieved remarkable performance with pre-trained models. These approaches expand a prompt pool by adding a new set of prompts while learning and select the correct set during inference. Previous studies have revealed that learning task-wised prompt sets individually and low selection accuracy pose challenges to the performance of PCL. In this paper, we propose a plug-in method, $\textbf{L}$earning $\textbf{W}$hether $\textbf{t}$o $\textbf{G}$row $\textbf{(LW2G)}$, which leverages the disparities between tasks to form an effective and efficient prompt sets pool, thereby achieving intra-task knowledge sharing and cooperation and avoiding the unbounded increase in the cost of the prompt pool. Specifically, a shared set is utilized when several tasks share certain commonalities, and a new set is added when there are significant differences between the new and previous tasks. To achieve this, we develop a metric called Hinder Forward Capability (HFC) to measure the hindrance imposed on learning new tasks by surgically modifying the original gradient onto the orthogonal complement of the old feature space. With HFC, an automated scheme, Dynamic Growing Approach, adaptively learns whether to grow with a dynamic threshold. Furthermore, we design a gradient-based constraint to ensure consistency between the updating prompts and pre-trained knowledge. Extensive experiments show the effectiveness of our method. Code is available at https://github.com/RAIAN08/LW2G.

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。

↑