唯有曲线形状重要：通过下一个曲线形状预测训练零样本多变量时间序列预测的基础模型
Only the Curve Shape Matters: Training Foundation Models for Zero-Shot Multivariate Time Series Forecasting through Next Curve Shape Prediction
AI总结：
提出General Time Transformer (GTT)，通过将多变量时间序列预测表述为通道级下一个曲线形状预测问题进行预训练，在零样本预测中超越监督基线并验证了缩放律。
摘要：
我们提出了 General Time Transformer (GTT)，这是一种用于零样本多变量时间序列预测的仅编码器风格基础模型。GTT 在包含 200M 高质量时间序列样本且跨越多个领域的大型数据集上进行了预训练。在我们提出的框架中，多变量时间序列预测任务被表述为通道级的下一个曲线形状预测问题，其中每个时间序列样本被表示为具有统一数值幅度的非重叠曲线形状序列。GTT 被训练为以通道级方式基于过去曲线形状的窗口预测下一个曲线形状。实验结果表明，GTT 在未见时间序列数据集上展现出卓越的零样本多变量预测能力，甚至超越了最先进的监督基线。此外，我们研究了改变 GTT 模型参数和训练数据集规模的影响，观察到缩放律在零样本多变量时间序列预测的背景下同样成立。
英文摘要：
We present General Time Transformer (GTT), an encoder-only style foundation model for zero-shot multivariate time series forecasting. GTT is pretrained on a large dataset of 200M high-quality time series samples spanning diverse domains. In our proposed framework, the task of multivariate time series forecasting is formulated as a channel-wise next curve shape prediction problem, where each time series sample is represented as a sequence of non-overlapping curve shapes with a unified numerical magnitude. GTT is trained to predict the next curve shape based on a window of past curve shapes in a channel-wise manner. Experimental results demonstrate that GTT exhibits superior zero-shot multivariate forecasting capabilities on unseen time series datasets, even surpassing state-of-the-art supervised baselines. Additionally, we investigate the impact of varying GTT model parameters and training dataset scales, observing that the scaling law also holds in the context of zero-shot multivariate time series forecasting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
