让时间序列模型学会看例子就懂新任务，无需重新训练。
In-context Pre-trained Time-Series Foundation Models adapt to Unseen Tasks
- 用上下文学习能力重构预训练数据，让模型能动态适应新任务。
- 在未见过的任务上性能提升约11.4%，无需微调。
- 适合需要快速适配新场景的时间序列应用。
时间序列基础模型（TSFMs）已在多种数据集和任务中展现出强大的泛化能力。然而，现有基础模型通常针对特定任务进行预训练，难以在不微调的情况下泛化到未见任务。为此，我们提出为TSFMs引入上下文学习（ICL）能力，使其能在测试时通过输入输出示例动态适应新任务。我们的框架In-Context Time-series Pre-training（ICTP）重构原始预训练数据，使主干TSFM具备ICL能力，从而实现对未见任务的自适应。实验表明，该方法在无需微调的情况下，使当前最先进TSFMs在未见任务上的性能平均提升约11.4%。
原文摘要 · Abstract (English)
Time-series foundation models (TSFMs) have demonstrated strong generalization capabilities across diverse datasets and tasks. However, existing foundation models are typically pre-trained to enhance performance on specific tasks and often struggle to generalize to unseen tasks without fine-tuning. To address this limitation, we propose augmenting TSFMs with In-Context Learning (ICL) capabilities, enabling them to perform test-time inference by dynamically adapting to input-output relationships provided within the context. Our framework, In-Context Time-series Pre-training (ICTP), restructures the original pre-training data to equip the backbone TSFM with ICL capabilities, enabling adaptation to unseen tasks. Experiments demonstrate that ICT improves the performance of state-of-the-art TSFMs by approximately 11.4% on unseen tasks without requiring fine-tuning.
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。