arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2505.04575cs.CVcs.LG
收藏

面向域增量学习的组件化提示-知识对齐

Componential Prompt-Knowledge Alignment for Domain Incremental Learning

Amazon.com, Inc(亚马逊公司)

Kunlun Xu, Xu Zou, Gang Hua, Jiahuan Zhou

AI总结:

针对域增量学习中提示组件错位导致知识冲突的问题,本文提出KA-Prompt方法,通过组件结构配置和在线对齐保持实现新旧提示间的组件级知识对齐,显著提升模型学习与推理性能。

摘要:

域增量学习(DIL)旨在从跨域的非平稳数据流中学习,同时保留并利用过去的知识。尽管基于提示(prompt)的方法能够有效地将多域知识存储在提示参数中,并通过跨域提示融合获得先进性能,但我们揭示了一个内在局限:域特定提示之间的组件级错位会导致冲突的知识整合和退化的预测。这源于知识组件在提示内部的随机定位,其中不相关组件的融合会引入干扰。为解决这一问题,我们提出了组件化提示-知识对齐(KA-Prompt),这是一种新颖的基于提示的DIL方法,在训练过程中引入组件感知的提示-知识对齐,显著提升了模型的学习和推理能力。KA-Prompt分两个阶段运行:(1)初始组件结构配置,通过贪心搜索挖掘一组包含与新域相关知识的旧提示,然后利用这些旧提示初始化新提示,以实现可复用的知识迁移,并在新旧提示之间建立内在对齐。(2)在线对齐保持,随着新提示的演化,动态识别目标旧提示并施加自适应的组件一致性约束。在DIL基准上的大量实验证明了我们KA-Prompt的有效性。我们的源代码可在 https://github.com/zhoujiahuan1991/ICML2025-KA-Prompt 获取。

英文摘要:

Domain Incremental Learning (DIL) aims to learn from non-stationary data streams across domains while retaining and utilizing past knowledge. Although prompt-based methods effectively store multi-domain knowledge in prompt parameters and obtain advanced performance through cross-domain prompt fusion, we reveal an intrinsic limitation: component-wise misalignment between domain-specific prompts leads to conflicting knowledge integration and degraded predictions. This arises from the random positioning of knowledge components within prompts, where irrelevant component fusion introduces interference.To address this, we propose Componential Prompt-Knowledge Alignment (KA-Prompt), a novel prompt-based DIL method that introduces component-aware prompt-knowledge alignment during training, significantly improving both the learning and inference capacity of the model. KA-Prompt operates in two phases: (1) Initial Componential Structure Configuring, where a set of old prompts containing knowledge relevant to the new domain are mined via greedy search, which is then exploited to initialize new prompts to achieve reusable knowledge transfer and establish intrinsic alignment between new and old prompts. (2) Online Alignment Preservation, which dynamically identifies the target old prompts and applies adaptive componential consistency constraints as new prompts evolve. Extensive experiments on DIL benchmarks demonstrate the effectiveness of our KA-Prompt. Our source code is available at https://github.com/zhoujiahuan1991/ICML2025-KA-Prompt

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。

↑