Align-RAG：TSFM上下文学习的全部需求在于对齐
Align-RAG: Alignment Is All You Need for TSFM In-Context Learning
浏览论文内容
中文总结 AI 辅助
提出无需训练的Align-RAG方法，通过闭式对齐检索窗口，在冻结TSFM上提升检索增强预测性能，证明冻结TSFM可动态整合检索结果，闭式对齐可作为默认基线。
中文摘要 AI 辅助
检索增强预测有望在不微调的情况下将冻结的时间序列基础模型（TSFM）适配到新领域，但近期方法通常依赖学习得到的融合模块，即训练好的适配器，该适配器基于冻结的主干模型无法自行动态整合检索到的上下文这一假设，将检索到的示例合并到主干模型的预测中。我们证明这一假设并非必要。我们提出Align-RAG，一种无需训练的方法，在检索到的过去-未来窗口进入冻结主干模型的上下文前，对其应用闭式逐对振幅重缩放和整数滞后相移。由于无需学习参数，Align-RAG在标准基准的全部七个数据集上，于冻结Chronos-Bolt模型上优于最先进的训练型检索适配器（平均MSE降低3.75%），表明此前归因于学习型融合的收益可在无需任何训练的情况下实现。Align-RAG还在四个额外的具有不同架构的冻结TSFM上将零样本MSE提升了2.5%至13.7%，且无需针对每个主干模型进行调整。为探究对齐为何有帮助，我们比较了冻结主干模型在对齐演示下的预测偏移，与相同配对下闭式岭回归预测偏移的差异，发现对齐演示诱导的预测偏移与相同配对下的闭式岭回归预测器轨迹一致，而未来洗牌对照实验排除了未来平均的解释。综上，这些结果表明，冻结TSFM已支持对检索结果进行动态上下文使用，且在训练任何融合模块前，闭式对齐应作为检索增强预测的默认基线。代码可访问：this https URL
英文摘要
Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption is unnecessary. We introduce Align-RAG, a training-free method that applies a closed-form per-pair amplitude rescaling and integer-lag phase shift to retrieved past-future windows before they enter a frozen backbone's context. With no learned parameters, Align-RAG outperforms the state-of-the-art trained retrieval adapter on a frozen Chronos-Bolt on all seven datasets of the standard benchmark (avg -3.75% MSE), showing that the gains previously attributed to learned fusion are recoverable without any training. Align-RAG further improves zero-shot MSE on four additional frozen TSFMs with various architectures by 2.5% to 13.7% per backbone with no per-backbone tuning. To probe why alignment helps, we compare the frozen backbone's prediction shift under aligned demonstrations to the closed-form ridge prediction shift on the same pairs. We find that aligned demonstrations induce prediction shifts that track a closed-form ridge predictor on the same pairs, with a future-shuffle control ruling out a futures-averaging account. Together, these results indicate that frozen TSFMs already support dynamic in-context use of retrievals, and that closed-form alignment should be the default baseline for retrieval-augmented forecasting before any fusion module is trained. Code available at: https://github.com/masadi-99/align-rag
发表机构
- Stanford University（斯坦福大学）
- Amazon（亚马逊公司）
机构由 AI 辅助整理，请以论文原文为准。
