参数高效的持续学习方法：在有限模型容量下提升可塑性且不遗忘
Parameter-efficient Continual Learning for Enhancing Plasticity without Forgetting under Limited Model Capacity
在模型容量受限时，用梯度引导的冻结参数复用加强化学习式参数分配来平衡稳定性与可塑性，可直接迁移到视觉骨干（如 ViT）的长序列增量微调，避免每来一个新任务就扩参数。
原文依据 a gradient-guided parameter reuse strategy is proposed to make full use of frozen parameters while ensuring that no task interference is introduced
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论避免对先前任务的灾难性遗忘，并保持模型支持新任务的可塑性，是持续学习的两个关键目标。然而，现有方法通常忽视其中一方面，难以在长任务序列上取得令人满意的性能，在模型规模受限的资源受限场景中尤为如此。本文提出 GRAPA，一种参数高效的持续学习方法，能够良好地平衡模型的稳定性与可塑性，以处理复杂度各异的长任务序列。GRAPA 通过两项新颖设计在不牺牲稳定性的前提下增强模型可塑性。首先，提出梯度引导的参数复用策略，在确保不引入任务干扰的同时充分利用冻结参数。其次，设计基于强化学习的参数分配机制，使模型能够在复用参数之上适应当前任务，同时为未来任务保留最大的模型容量。在由多个数据集构成的多个任务序列上的实验表明，GRAPA 将平均任务准确率最高提升 7.67%，在后续复杂任务上最高提升 14.92%，体现了 GRAPA 优越的可塑性。
英文原文摘要 1242 字符
Avoiding catastrophic forgetting for previous tasks and maintaining model plasticity to support new tasks are two critical objectives of continual learning. However, existing methods usually neglect one of the two aspects and fail to support long task sequences with satisfactory performance, especially in resource-constrained scenarios in which the size of the model is limited. This work proposes GRAPA, a parameter-efficient continual learning method that well balances stability and plasticity of the model to handle long task sequences with diverse complexities. GRAPA enhances model plasticity without sacrificing stability with two novel designs. First, a gradient-guided parameter reuse strategy is proposed to make full use of frozen parameters while ensuring that no task interference is introduced. Second, a reinforcement-learning-based parameter allocation is designed to enable the model to adapt to the current task on top of reused parameters while preserving maximal model capacity for future tasks. Experiments on multiple task sequences composed of various datasets demonstrate that GRAPA lifts mean task accuracy by up to 7.67%, with up to 14.92% gains on subsequent complex tasks, reflecting GRAPA's superior plasticity.