Adapter-based methods have become a cost-effective approach to continual learning (CL) for Large Language Models (LLMs), by sequentially learning a low-rank update matrix for each task. To mitigate catastrophic forgetting, state-of-the-art approaches impose constraints on new adapters with respect to the previous ones, by targeting either subspace or coordinate-wise interference. In this paper, we propose JumpLoRA, a novel framework to adaptively induce sparsity in the Low-Rank Adaptation (LoRA) blocks through the use of JumpReLU gating. The method achieves dynamic parameter isolation, which helps prevent task interference. We demonstrate that our method is highly modular and compatible with LoRA-based CL approaches. Specifically, it significantly boosts the performance of IncLoRA and outperforms the leading state-of-the-art CL method, ELLA.

翻译：基于适配器的方法通过为每个任务顺序学习低秩更新矩阵，已成为大语言模型持续学习中一种经济高效的策略。为缓解灾难性遗忘，现有前沿技术通过针对子空间或坐标方向干扰对新适配器施加相对于先前适配器的约束。本文提出JumpLoRA这一新型框架，利用JumpReLU门控机制自适应地在低秩适配（LoRA）模块中诱导稀疏性。该方法实现了动态参数隔离，有助于防止任务干扰。我们证明该方法具有高度模块化特性，可与基于LoRA的持续学习方法兼容。具体而言，它能显著提升IncLoRA的性能，并超越当前领先的持续学习方法ELLA。