A recent trend is to develop forecasting models based on graph neural networks (GNNs). However, existing GNN-based methods suffer from two key limitations: (1) current models broaden receptive fields by scaling the depth of GNNs, which is insufficient to preserve the semantics of long-range ...
and MartinaZannotti 1,31 University of Camerino2 University of Siena3 Syeew s.r.lOctober 2024AbstractIn recent years, spatio-temporal graph neural networks (GNNs) have attracted considerableinterest in the f i eld of time series analysis, due to their ability to capture dependencies amongvariables...
11. Next POI Recommendation with Dynamic Graph and Explicit Dependency 12. Scalable Spatiotemporal Graph Neural Networks 13. Learning Decomposed Spatial Relations for Multi-Variate Time-Series Modeling 14. c-NTPP: Learning Cluster-Aware Neural Temporal Point Process 15. Trafformer: Unify Time and Spa...
Taken together Eqs. (5) and (6) define a message passing round that propagates information one hop further than the previous round. For instance, one of the very first graph neural networks, namely the graph convolutional network57, proposed the following functions: $$\begin{aligned}&M_r^{...
A Graph Neural Network with Spatio-Temporal Attention for Multi-Sources Time Series Data: An Application to Frost Forecast frost forecastinggraph neural networksspatio-temporal attentionFrost forecast is an important issue in climate research because of its economic impact on several... N Sanchez-Pi ...
Graph CNNs for Extracting Spatial Features 首先使用图卷积来捕获空间相关性,本篇论文采用的是切比雪夫近似与一阶近似后的图卷积公式,我们只看最终的那个卷积公式,其中D为图的度矩阵,A_hat为图的邻接矩阵+单位矩阵,为的是在卷积过程中不仅考虑邻居节点的状态,也考虑自身的状态。
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 the directionality of traffic flows. Furthermore, different spatial dependency patterns can ...
Temporal Graph Neural Network based on Gated Convolution and Topological Attention (STGNN-GCTA) to accurately model complex spatiotemporal traffic flow ... D Bai,D Xia,YLH Huang - Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Te...
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 the directionality of traffic flows. Furthermore, different spatial dependency patterns can ...
Spatio-temporal graph convolutional neural network for remaining useful life estimation of aircraft engines 来自 Semantic Scholar 喜欢 0 阅读量: 98 作者:M Wang,Y Li,Y Zhang,L Jia 摘要: Aerospace Systems - DOI: 10.1007/s42401-021-00108-8 ...