4 Hits in 3.1 sec

Graph Neural Controlled Differential Equations for Traffic Forecasting [article]

Jeongwhan Choi, Hwangyong Choi, Jeehyun Hwang, Noseong Park
2021 arXiv   pre-print
A prevalent approach in the field is to combine graph convolutional networks and recurrent neural networks for the spatio-temporal processing.  ...  Traffic forecasting is one of the most popular spatio-temporal tasks in the field of machine learning.  ...  Z-GCNETs (Chen, Segovia-Dominguez, and Gel 2021) integrates the new timeaware zigzag topological layer into time-conditioned GCNs.  ... 
arXiv:2112.03558v1 fatcat:rsujmg5zdvh7lecjlh42xsydey

Spatio-Temporal Joint Graph Convolutional Networks for Traffic Forecasting [article]

Chuanpan Zheng, Xiaoliang Fan, Shirui Pan, Zonghan Wu, Cheng Wang, Philip S. Yu
2021 arXiv   pre-print
To overcome these limitations, we propose a Spatio-Temporal Joint Graph Convolutional Networks (STJGCN) for traffic forecasting over several time steps ahead on a road network.  ...  In such a graph, the correlations between different nodes at different time steps are not explicitly reflected, which may restrict the learning ability of graph neural networks.  ...  ACKNOWLEDGMENT The research is supported by Natural Science Foundation of China (61872306), Xiamen Science and Technology Bureau (3502Z20193017) and Fundamental Research Funds for the Central Universities  ... 
arXiv:2111.13684v2 fatcat:4piif3m5rrgejomvavvfi6yrdy

Dynamic Adaptive and Adversarial Graph Convolutional Network for Traffic Forecasting [article]

Juyong Jiang, Binqing Wu, Ling Chen, Sunghun Kim
2022 arXiv   pre-print
To this end, in this paper, we propose a Dynamic Adaptive and Adversarial Graph Convolutional Network (DAAGCN), which combines Graph Convolution Networks (GCNs) with Generative Adversarial Networks (GANs  ...  ) for traffic forecasting.  ...  for graph convolution and GRU to model temporal correlations; Z-GCNETs (Chen, Segovia, and Gel 2021), integrating the new time-aware zigzag topological layer into time-conditioned GCNs.  ... 
arXiv:2208.03063v1 fatcat:u6as555dvnenzdunlboodrlolm

Regularized Graph Structure Learning with Semantic Knowledge for Multi-variates Time-Series Forecasting

Hongyuan Yu, Ting Li, Weichen Yu, Jianguo Li, Yan Huang, Liang Wang, Alex Liu
2022 Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence   unpublished
Multivariate time-series forecasting is a critical task for many applications, and graph time-series network is widely studied due to its capability to capture the spatial-temporal correlation simultaneously  ...  In this paper, we propose Regularized Graph Structure Learning (RGSL) model to incorporate both explicit prior structure and implicit structure together, and learn the forecasting deep networks along with  ...  features; GCNs with a time-aware zigzag topological layer (Z-GCNETs) [Chen et al., 2021b] introduces the concept of zigzag persistence into time-aware GCN.  ... 
doi:10.24963/ijcai.2022/325 fatcat:6pam2yemxbemrij3mc3in5lkhy