PLAN：用于持续学习的主动低秩分配
PLAN: Proactive Low-Rank Allocation for Continual Learning
AI总结：
本文提出PLAN框架，通过主动分配正交低秩子空间并采用扰动优化与敏感性选择机制，在持续学习中高效微调大型预训练模型，避免遗忘并刷新基准性能。
摘要：
持续学习（CL）要求模型在不断适应新任务的同时不遗忘已有知识。在本工作中，我们提出了主动低秩分配（PLAN），这是一个扩展低秩适应（LoRA）的框架，以在持续学习环境中实现对大型预训练模型的高效且干扰感知的微调。PLAN通过为每个任务引入正交基向量，并采用基于扰动的策略对其进行优化，以最小化与先前学习参数的冲突，从而主动管理任务特定子空间的分配。此外，PLAN还包含一种新颖的选择机制，该机制识别并分配对干扰具有最小敏感性的基向量，在保持对新任务高效适应的同时，降低退化已有知识的风险。在标准持续学习基准上的实验结果表明，PLAN始终优于现有方法，为基于基础模型的持续学习确立了新的最先进水平。
英文摘要：
Continual learning (CL) requires models to continuously adapt to new tasks without forgetting past knowledge. In this work, we propose \underline{P}roactive \underline{L}ow-rank \underline{A}llocatio\underline{N} (PLAN), a framework that extends Low-Rank Adaptation (LoRA) to enable efficient and interference-aware fine-tuning of large pre-trained models in CL settings. PLAN proactively manages the allocation of task-specific subspaces by introducing orthogonal basis vectors for each task and optimizing them through a perturbation-based strategy that minimizes conflicts with previously learned parameters. Furthermore, PLAN incorporates a novel selection mechanism that identifies and assigns basis vectors with minimal sensitivity to interference, reducing the risk of degrading past knowledge while maintaining efficient adaptation to new tasks. Empirical results on standard CL benchmarks demonstrate that PLAN consistently outperforms existing methods, establishing a new state-of-the-art for continual learning with foundation models.
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。
