TraverseNet: Unifying Space and Time in Message Passing
- URL: http://arxiv.org/abs/2109.02474v1
- Date: Wed, 25 Aug 2021 04:35:08 GMT
- Title: TraverseNet: Unifying Space and Time in Message Passing
- Authors: Zonghan Wu, Da Zheng, Shirui Pan, Quan Gan, Guodong Long, George
Karypis
- Abstract summary: This paper aims to unify spatial dependency and temporal dependency in a non-Euclidean space.
We propose TraverseNet, a novel spatial-temporal graph neural network, viewing space and time as an inseparable whole.
- Score: 46.12086583451224
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: This paper aims to unify spatial dependency and temporal dependency in a
non-Euclidean space while capturing the inner spatial-temporal dependencies for
spatial-temporal graph data. For spatial-temporal attribute entities with
topological structure, the space-time is consecutive and unified while each
node's current status is influenced by its neighbors' past states over variant
periods of each neighbor. Most spatial-temporal neural networks study spatial
dependency and temporal correlation separately in processing, gravely impaired
the space-time continuum, and ignore the fact that the neighbors' temporal
dependency period for a node can be delayed and dynamic. To model this actual
condition, we propose TraverseNet, a novel spatial-temporal graph neural
network, viewing space and time as an inseparable whole, to mine
spatial-temporal graphs while exploiting the evolving spatial-temporal
dependencies for each node via message traverse mechanisms. Experiments with
ablation and parameter studies have validated the effectiveness of the proposed
TraverseNets, and the detailed implementation can be found from
https://github.com/nnzhan/TraverseNet.
Related papers
- Linear Attention is Enough in Spatial-Temporal Forecasting [0.0]
We propose treating nodes in road networks at different time steps as independent spatial-temporal tokens.
We then feed them into a vanilla Transformer to learn complex spatial-temporal patterns.
Our code achieves state-of-the-art performance at an affordable computational cost.
arXiv Detail & Related papers (2024-08-17T10:06:50Z) - DSTCGCN: Learning Dynamic Spatial-Temporal Cross Dependencies for
Traffic Forecasting [7.3669718660909735]
We propose a dynamic spatial-temporal cross graph convolution network to learn dynamic spatial and temporal dependencies jointly.
Experiments on six real-world datasets demonstrate that DSTCGCN achieves the state-of-the-art performance.
arXiv Detail & Related papers (2023-07-02T08:53:10Z) - Temporal Aggregation and Propagation Graph Neural Networks for Dynamic
Representation [67.26422477327179]
Temporal graphs exhibit dynamic interactions between nodes over continuous time.
We propose a novel method of temporal graph convolution with the whole neighborhood.
Our proposed TAP-GNN outperforms existing temporal graph methods by a large margin in terms of both predictive performance and online inference latency.
arXiv Detail & Related papers (2023-04-15T08:17:18Z) - Spatial-Temporal Graph Convolutional Gated Recurrent Network for Traffic
Forecasting [3.9761027576939414]
We propose a novel framework for traffic forecasting, named Spatial-Temporal Graph Convolutional Gated Recurrent Network (STGCGRN)
We design an attention module to capture long-term dependency by mining periodic information in traffic data.
Experiments on four datasets demonstrate the superior performance of our model.
arXiv Detail & Related papers (2022-10-06T08:02:20Z) - Spatio-Temporal Joint Graph Convolutional Networks for Traffic
Forecasting [75.10017445699532]
Recent have shifted their focus towards formulating traffic forecasting as atemporal graph modeling problem.
We propose a novel approach for accurate traffic forecasting on road networks over multiple future time steps.
arXiv Detail & Related papers (2021-11-25T08:45:14Z) - LSTA-Net: Long short-term Spatio-Temporal Aggregation Network for
Skeleton-based Action Recognition [14.078419675904446]
LSTA-Net: a novel short-term Spatio-Temporal Network.
Long/short-term temporal information is not well explored in existing works.
Experiments were conducted on three public benchmark datasets.
arXiv Detail & Related papers (2021-11-01T10:53:35Z) - Space-Time Graph Neural Networks [104.55175325870195]
We introduce space-time graph neural network (ST-GNN) to jointly process the underlying space-time topology of time-varying network data.
Our analysis shows that small variations in the network topology and time evolution of a system does not significantly affect the performance of ST-GNNs.
arXiv Detail & Related papers (2021-10-06T16:08:44Z) - Spatial-Temporal Fusion Graph Neural Networks for Traffic Flow
Forecasting [35.072979313851235]
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.
This paper proposes Spatial-Temporal Fusion Graph Neural Networks (STFGNN) for traffic flow forecasting.
arXiv Detail & Related papers (2020-12-15T14:03:17Z) - A Spatial-Temporal Attentive Network with Spatial Continuity for
Trajectory Prediction [74.00750936752418]
We propose a novel model named spatial-temporal attentive network with spatial continuity (STAN-SC)
First, spatial-temporal attention mechanism is presented to explore the most useful and important information.
Second, we conduct a joint feature sequence based on the sequence and instant state information to make the generative trajectories keep spatial continuity.
arXiv Detail & Related papers (2020-03-13T04:35:50Z) - Spatial-Temporal Transformer Networks for Traffic Flow Forecasting [74.76852538940746]
We propose a novel paradigm of Spatial-Temporal Transformer Networks (STTNs) to improve the accuracy of long-term traffic forecasting.
Specifically, we present a new variant of graph neural networks, named spatial transformer, by dynamically modeling directed spatial dependencies.
The proposed model enables fast and scalable training over a long range spatial-temporal dependencies.
arXiv Detail & Related papers (2020-01-09T10:21:04Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.