3.5 Spatio-Temporal Graph Transformer 时间transformer可以单独模拟每个行人的运动动力学,但不能考虑空间交互作用;spatial Transformer利用TGConv处理人群交互,但很难推广到时间序列。行人预测的一个主要挑战是建模耦合时空交互作用。行人的空间和时间动态密切相关。例如,当一个人决定她的下一个动作时,她首先会预测她的...
在时间维度上,对每个行人单独考虑,应用temporal Transformer抽取时许相关性; 即使是时许上的Transformer,也提供了比RNN更好的表现; 在空间维度上,引入TGConv--Transformer-based message passing graph convolution mechanism。相较于传统的图卷积抽取行人之间的交互关系,采用TGConv在高人群密度、复杂交互关系的情形下能...
In this paper, we present STAR, a\nSpatio-Temporal grAph tRansformer framework, which tackles trajectory\nprediction by only attention mechanisms. STAR models intra-graph crowd\ninteraction by TGConv, a novel Transformer-based graph convolution mechanism.\nThe inter-graph temporal dependencies are ...
In this paper, we present STAR, a Spatio-Temporal grAph tRansformer framework, which tackles trajectory prediction by only attention mechanisms. STAR models intra-graph crowd interaction by TGConv, a novel Transformer-based graph convolution mechanism. The inter-graph temporal dependencies are modeled ...
论文精读|2024[KDD]ImputeFormer: 用于广义时空补全的低秩诱导的Transformer ImputeFormer 21. Pre-Training Identification of Graph Winning Tickets in Adaptive Spatial-Temporal Graph Neural Networks 链接:https://arxiv.org/abs/2406.08287 ACM链接:https://dl.acm.org/doi/abs/10.1145/3637528.3671912 ...
For instance, research [34] introduces a spatial-temporal graph transformer network (STGTN), integrating a transformer with an external attention mechanism and graph convolutional layer for advanced short-term wind speed forecasting. It uses a multilayer perceptron (MLP) for temporal analysis, ...
Traffic prediction is a vital aspect of Intelligent Transportation Systems with widespread applications. The main challenge is accurately modeling the complex spatial and temporal relationships in traffic data. Spatial鈥搕emporal Graph Neural Networks (GNNs) have emerged as one of the most promising meth...
(2023), "STCGCN: a spatio-temporal complete graph convolutional network for remaining useful life prediction of power transformer", International Journal of Web Information Systems, Vol. 19 No. 2, pp. 102-117. https://doi.org/10.1108/IJWIS-02-2023-0023 Download as .RIS Publisher...
此文提出了一个基于Transformer名为ST-GRAT的交通预测模型使用self-attention捕捉时空间依赖。 此文对于self-attention做出改进,首先对于spatial attention加上路网信息先验,然后对于spatial和temporal attention都使用sentinel,sentinel可以自适应的选择保留原始信息或者获取新信息。
Spatial-Temporal Transformer Networks for Traffic Flow Forecastingarxiv.org/abs/2001.02908 It presents a new variant of graph neural networks, named spatial transformer, by dynamically modeling directed spatial dependencies with self-attention mechanism to capture real-time traffic conditions as well as...