1.【交通流】现有框架通常利用给定的空间邻接图和复杂的机制来建模空间和时间相关性。然而,具有不完全相邻连接的给定空间图结构的有限表示可能会限制这些模型的有效时空依赖性学习。此外,在解决复杂的时空数据时,现有的方法已经无能为力:它们通常利用独立的模块来实现空间和时间相关性,或者它们只使用独立的组件来捕获局部或全局的异构依赖关系。
原文:Spatial-temporal data forecasting of traffic flow is a challenging task because of complicated spatial dependencies and dynamical trends of temporal pattern between different roads. Existing frameworks typically utilize given spatial adjacency graph and sophisticated mechanisms for modeling spatial and temporal correlations. However, limited representations of given spatial graph structure with incomplete adjacent connections may restrict effective spatial-temporal dependencies learning of those models. Furthermore, existing methods are out at elbows when solving complicated spatial-temporal data: they usually utilize separate modules for spatial and temporal correlations, or they only use independent components capturing localized or global heterogeneous dependencies.
来源:《Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow Forecasting》