通过子空间对齐更新，解决持续学习中的遗忘问题
Resolving Conflicts in Lifelong Learning via Aligning Updates in Subspaces
- 在优化子空间中对齐新旧任务梯度方向，减少冲突
- 在多个NLP和视觉基准上超越现有方法，保持稳定性能
- 适合需要高效适应新任务且避免遗忘的持续学习场景
低秩适应（LoRA）虽能实现高效持续学习，但常因任务间梯度破坏性干扰导致灾难性遗忘。分析表明，性能下降主要源于新任务梯度与历史权重轨迹方向相反。为此，我们提出PS-LoRA（参数稳定性LoRA），通过双正则化目标惩罚冲突方向并约束幅度偏差，确保与先验知识一致。此外，采用基于幅度的融合策略，无需重训练即可将序列适配器合并为鲁棒表示。在NLP和视觉基准上的实验表明，PS-LoRA在保持学习表征稳定性的同时，有效适应新领域，性能优于当前最优方法。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。