参数隔离对基于提示词的持续学习更有效吗？
Is Parameter Isolation Better for Prompt-Based Continual Learning?
把「每任务一组提示词」的静态隔离换成全局提示词池 + 任务感知门控稀疏路由，可直接迁移到视觉持续学习（如类增量图像分类、VLM 持续适配）中，用激活统计做正则来抑制常用提示词被过度更新。
原文依据 constructs a global prompt pool and introduces a task-aware gated routing mechanism that sparsely activates a subset of prompts
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论基于提示词的持续学习方法能有效缓解灾难性遗忘。然而，现有方法大多为每个任务分配一组固定的提示词，将不同任务的知识完全隔离，导致参数利用率欠佳。针对这一问题，我们结合持续学习的实际需求，提出一种提示词共享框架。该框架构建全局提示词池，并引入任务感知的门控路由机制，稀疏地激活一部分提示词，从而实现任务特定特征表示的动态解耦与协同优化。此外，我们引入历史感知调制器，利用累积的提示词激活统计量保护被频繁使用的提示词免于过度更新，从而缓解参数使用低效与知识遗忘问题。大量分析与实证结果表明，我们的方法在有效性和效率上均持续优于现有的静态分配策略。代码与模型将公开。
英文原文摘要 1052 字符
Prompt-based continual learning methods effectively mitigate catastrophic forgetting. However, most existing methods assign a fixed set of prompts to each task, completely isolating knowledge across tasks and resulting in suboptimal parameter utilization. To address this, we consider the practical needs of continual learning and propose a prompt-sharing framework. This framework constructs a global prompt pool and introduces a task-aware gated routing mechanism that sparsely activates a subset of prompts to achieve dynamic decoupling and collaborative optimization of task-specific feature representations. Furthermore, we introduce a history-aware modulator that leverages cumulative prompt activation statistics to protect frequently used prompts from excessive updates, thereby mitigating inefficient parameter usage and knowledge forgetting. Extensive analysis and empirical results demonstrate that our approach consistently outperforms existing static allocation strategies in effectiveness and efficiency. Code and models will be released.