通过在子空间中对齐更新来解决终身学习中的冲突
Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
AI总结：
PS-LoRA通过在优化子空间中对齐更新，解决终身学习中的冲突问题，提升模型在新领域适应时的稳定性与效率。
摘要：
低秩适应（LoRA）能够实现高效的持续学习，但常常因任务之间的破坏性干扰而产生灾难性遗忘。我们的分析表明，这种退化主要是由对抗性方向更新驱动的，其中新任务的梯度直接与历史权重轨迹相反。为了解决这个问题，我们提出了PS-LoRA（参数稳定性LoRA），一种旨在通过在优化子空间内对齐更新来解决冲突的框架。我们的方法采用了一个双正则化目标，该目标惩罚冲突方向并限制幅度偏差，以确保与先前知识的一致性。此外，我们实现了基于幅度的合并策略，以将连续的适配器合并为一个稳健的表示，而无需重新训练。在NLP和视觉基准测试中，PS-LoRA在保持学习表示的稳定性的同时，能够高效地适应新领域，优于当前最先进的方法。
英文摘要：
Low-Rank Adaptation (LoRA) enables efficient Continual Learning but often suffers from catastrophic forgetting due to destructive interference between tasks. Our analysis reveals that this degradation is primarily driven by antagonistic directional updates where new task gradients directly oppose the historical weight trajectory. To address this, we propose PS-LoRA (Parameter Stability LoRA), a framework designed to resolve conflicts by aligning updates within the optimization subspace. Our approach employs a dual-regularization objective that penalizes conflicting directions and constrains magnitude deviations to ensure consistency with prior knowledge. Additionally, we implement a magnitude-based merging strategy to consolidate sequential adapters into a robust representation without retraining. Experiments on NLP and Vision benchmarks show that PS-LoRA outperforms state-of-the-art methods by preserving the stability of learned representations while efficiently adapting to new domains.
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。
