WorldTS：面向多模态协变量感知时间序列预测的世界建模

中文摘要 AI 辅助

时间序列预测通常被框架化为在观测空间中学习从历史观测到未来观测的直接映射。然而，观测序列通常只能提供底层系统动力学的部分视图，未来观测受潜在动力学塑造。因此，最近的潜在空间预测方法通过从历史观测的潜在空间表示预测未来观测，而非直接在观测空间中预测未来观测，从而实现了性能提升。其次，虽然未来观测也受外部因素影响，但如何将外部（通常是多模态的）信息纳入预测，使其能直接塑造潜在状态的形成与演化，仍探索不足。我们提出WorldTS，一种基于世界建模的预测框架，将多模态协变量直接整合进预测，以进一步提升预测性能。具体而言，WorldTS采用两阶段训练策略。首先，它学习以多模态协变量为条件的预测相关潜在状态动力学，生成编码的未来状态。接着，冻结学习到的状态动力学，训练一个观测解码器将预测的未来状态映射回未来观测。在21个真实世界数据集上的大量实验为WorldTS及其有效性提供了洞见。

英文摘要

Time series forecasting is typically framed as learning a direct mapping from historical to future observations in the observation space. However, sequences of observations generally provide only a partial view of the dynamics of the underlying system, with future observations being shaped by latent dynamics. Recent latent-space forecasting methods thus achieve improved performance by predicting future observations from latent-space representations of historical observations rather than directly forecasting future observations in the observation space. Next, while future observations are also shaped by external factors, how to incorporate external, often multimodal, information into forecasting, so that it can shape latent-state formation and evolution directly, remains underexplored. We propose WorldTS, a world-modeling based forecasting framework that integrates multimodal covariates directly into the forecasting to further improve forecasting performance. Specifically, WorldTS employs a two-stage training strategy. First, it learns forecasting-relevant latent state dynamics conditioned on multimodal covariates, yielding encoded future states. Next, the learned state dynamics are frozen, and an observation decoder is trained to map the predicted future states back to future observations. Extensive experiments on 21 real-world datasets offer insight into WorldTS and its effectiveness.

发表机构

• East China Normal University（华东师范大学）
• Aalborg University（奥尔堡大学）

机构由 AI 辅助整理，请以论文原文为准。