FACTS:用于世界建模的因子化状态空间框架
FACTS: A Factored State-Space Framework For World Modelling
AI总结:
提出FACTS循环框架,利用图结构记忆与路由机制实现时空世界建模,支持并行计算,在多元时间序列、对象中心及时空图预测任务上优于或匹敌专门模型。
摘要:
世界建模对于通过学习空间和时间依赖关系来理解和预测复杂系统的动态至关重要。然而,当前的框架,如Transformer和选择性状态空间模型(如Mamba),在高效编码空间和时间结构方面表现出局限性,特别是在需要长期高维序列建模的场景中。为了解决这些问题,我们提出了一种新颖的循环框架,即因子化状态空间(FACTS)模型,用于时空世界建模。FACTS框架构建了一个带有路由机制的图结构记忆,该机制学习可置换的记忆表示,确保对输入置换的不变性,同时通过选择性状态空间传播进行适应。此外,FACTS支持高维序列的并行计算。我们在多种任务上对FACTS进行了实证评估,包括多元时间序列预测、以对象为中心的世界建模和时空图预测,结果表明,尽管其设计为通用世界建模,但它在这些任务上持续优于或匹配专门的最先进模型。
英文摘要:
World modelling is essential for understanding and predicting the dynamics of complex systems by learning both spatial and temporal dependencies. However, current frameworks, such as Transformers and selective state-space models like Mambas, exhibit limitations in efficiently encoding spatial and temporal structures, particularly in scenarios requiring long-term high-dimensional sequence modelling. To address these issues, we propose a novel recurrent framework, the \textbf{FACT}ored \textbf{S}tate-space (\textbf{FACTS}) model, for spatial-temporal world modelling. The FACTS framework constructs a graph-structured memory with a routing mechanism that learns permutable memory representations, ensuring invariance to input permutations while adapting through selective state-space propagation. Furthermore, FACTS supports parallel computation of high-dimensional sequences. We empirically evaluate FACTS across diverse tasks, including multivariate time series forecasting, object-centric world modelling, and spatial-temporal graph prediction, demonstrating that it consistently outperforms or matches specialised state-of-the-art models, despite its general-purpose world modelling design.
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。