提出动态扰动自适应方法，解决时间序列任务频繁冲突下的模型泛化难题。
Dynamic Perturbed Adaptive Method for Infinite Task-Conflicting Time Series
- 采用主干-分支架构，主干慢变捕长期结构，分支任务级重初始化更新。
- 在复杂冲突任务中显著优于基线，实现快速适应与渐进学习。
- 无需任务标签即可跨任务迁移，适合持续学习与动态环境应用。
我们将时间序列任务建模为在不同目标下的输入输出映射，同一输入可能对应不同输出，这对模型的泛化与适应能力构成挑战。为此，我们构建了一个包含大量冲突子任务的合成数据集，用于评估频繁任务切换下的适应性能。现有静态模型在此类场景中表现一致不佳。本文提出一种基于主干-分支架构的动态扰动自适应方法：主干模块缓慢演化以捕捉长期结构，分支模块针对每个任务重新初始化并更新。该设计支持测试时持续适应与跨任务迁移，且不依赖显式任务标签。理论上，我们证明该架构的功能表达能力严格高于静态模型和LoRA。同时，在Polyak-Lojasiewicz条件下，建立了分支适应的指数收敛性。实验表明，该方法在复杂且冲突的任务环境中显著优于竞争性基线，展现出快速适应与渐进学习能力。
原文摘要 · Abstract (English)
We formulate time series tasks as input-output mappings under varying objectives, where the same input may yield different outputs. This challenges a model's generalization and adaptability. To study this, we construct a synthetic dataset with numerous conflicting subtasks to evaluate adaptation under frequent task shifts. Existing static models consistently fail in such settings. We propose a dynamic perturbed adaptive method based on a trunk-branch architecture, where the trunk evolves slowly to capture long-term structure, and branch modules are re-initialized and updated for each task. This enables continual test-time adaptation and cross-task transfer without relying on explicit task labels. Theoretically, we show that this architecture has strictly higher functional expressivity than static models and LoRA. We also establish exponential convergence of branch adaptation under the Polyak-Lojasiewicz condition. Experiments demonstrate that our method significantly outperforms competitive baselines in complex and conflicting task environments, exhibiting fast adaptation and progressive learning capabilities.
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。