通过优化输入上下文提升时间序列模型预测精度，无需修改模型参数。
GITCO: Gated Inference-Time Context Optimization in TSFMs
- 引入门控机制在推理时筛选并抑制有害数据块。
- 在53个数据集上平均降低1.95% MASE误差，接近理论最优提升的90%。
- 揭示了模型对不同数据特征的敏感性，适用于高精度预测场景。
基于补丁的时间序列基础模型（TSFMs）存在上下文污染问题：结构异常的补丁会过度吸引注意力，无声降低零样本预测质量。我们提出在推理阶段优化输入上下文，而非修改模型权重，以提升TSFM精度。本文设计轻量级三组件框架GITCO（门控推理时上下文优化），包括门控单元、路由模块和评判器，可无参数更新地识别并抑制有害补丁。在TimesFM 2.5上，于53个GIFT-Eval数据集上进行K折交叉验证，GITCO实现平均1.95%的MASE降低，捕获了89.9%的性能提升上限。我们进一步提出上下文敏感性谱作为TSFM的新可表征属性：映射时间序列元特征至推理时上下文干预下的预期精度提升，由模型架构与数据统计结构共同决定。
原文摘要 · Abstract (English)
Patch-based Time Series Foundation Models (TSFMs) suffer from context poisoning: structurally anomalous patches capture disproportionate attention and silently degrade zero-shot forecast quality. We propose improving TSFM accuracy at inference time by optimizing the input context rather than modifying model weights. We present GITCO (Gated Inference-Time Context Optimization), a lightweight three-component framework: Gate, Router, and Critic that selectively identifies and suppresses harmful patches without any parameter updates. Evaluated on TimesFM 2.5 across 53 GIFT-Eval datasets under K-fold cross-validation, GITCO achieves an average +1.95% MASE reduction on TimesFM 2.5 while capturing 89.9% of the improvement upper bound. We introduce context sensitivity profiles as a new characterizable property of TSFMs: the mapping from time series meta-features to expected accuracy improvement under inference-time context intervention, shaped jointly by model architecture and the statistical structure of the data.
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。