BeliefGraph-JEPA：用于动作条件时间序列的结构化潜在世界模型

中文摘要 AI 辅助

动作条件时间序列预测需要考虑未来动作和外源强迫如何通过具有不同延迟和持续性的部分观测效应影响多个目标。直接条件化将这些效应的演变和目标特定影响隐含在预测器中，而静态关系图则指定连接而不跟踪演变效应。这促使通过结构化潜在状态来表示未来驱动因素的影响，这些状态在预测范围内演变并将信息路由到各个目标。我们引入了BeliefGraph-JEPA，一种结构化潜在世界模型，将驱动因素影响分解为类型化的潜在效应状态。这些状态在未来驱动因素下滚动，并通过图路由到目标特定节点，形成联合嵌入预测架构的预测基础。容量控制的残差补充了直接驱动因素信息。在四个多目标临床、农业、环境和工业系统中，该框架优于一系列预训练和监督的已知未来协变量基线。匹配对照隔离了潜在动态、未来滚动、图路由和残差容量；未来滚动和图优先残差路由改善了所有四个系统的预测。

英文摘要

Action-conditioned time-series forecasting requires accounting for how future actions and exogenous forcings influence multiple targets through partially observed effects with different delays and persistence. Direct conditioning leaves the evolution and target-specific influence of these effects implicit in the predictor, while static relational graphs specify connections without tracking evolving effects. This motivates representing future-driver influence through structured latent states that evolve over the forecast horizon and route information to individual targets. We introduce BeliefGraph-JEPA, a structured latent world model that factorizes driver influence into typed latent-effect states. These states are rolled forward under future drivers and routed through a graph to target-specific nodes, forming the predictive base of a joint-embedding predictive architecture. A capacity-controlled residual supplements this base with direct driver information. On four multi-target clinical, agricultural, environmental, and industrial systems, the framework outperforms a range of pretrained and supervised known-future-covariate baselines. Matched controls isolate latent dynamics, future rollout, graph routing, and residual capacity; future rollout and graph-first residual routing improve forecasting across all four systems.

发表机构

• Carnegie Mellon University（卡内基梅隆大学）
• University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）
• Stevens Institute of Technology（史蒂文斯理工学院）

机构由 AI 辅助整理，请以论文原文为准。