Published on Wed Aug 25 2021

TraverseNet: Unifying Space and Time in Message Passing

Zonghan Wu, Da Zheng, Shirui Pan, Quan Gan, Guodong Long, George Karypis
0
0
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.

Wed Mar 31 2021
Machine Learning
SST-GNN: Simplified Spatio-temporal Traffic forecasting model using Graph Neural Network
0
0
0
Sat Jun 13 2020
Machine Learning
Inductive Graph Neural Networks for Spatiotemporal Kriging
Time series forecasting and spatiotemporal kriging are the two most important tasks in data analysis. Recent research on graph neural networks has made substantial progress in time series forecasting. Little attention has been paid to the kriged problem -- recovering signals for unsampled locations/sensors.
0
0
0
Fri May 31 2019
Machine Learning
Graph WaveNet for Deep Spatial-Temporal Graph Modeling
Spatial-temporal graph modeling is an important task. Existing approaches mostly capture the spatial dependency on a fixed graph structure. By developing a novel adaptive dependency matrix and learn it through node embedding, our model can precisely capture the hidden spatial dependency in the data.
0
0
0
Wed Jul 15 2020
Machine Learning
On the Inclusion of Spatial Information for Spatio-Temporal Neural Networks
0
0
0
Mon Mar 16 2020
Computer Vision
GraphTCN: Spatio-Temporal Interaction Modeling for Human Trajectory Prediction
Predicting the future paths of an agent's neighbors accurately and in a rapidly manner is central to the autonomous applications for collision avoidance. Conventional approaches, e.g., LSTM-based models, take considerable computational costs in the prediction, especially for the long sequence.
0
0
0
Thu Apr 23 2020
Machine Learning
Spatiotemporal data analysis with chronological networks
The amount and size of spatiotemporal data sets from different domains have rapidly increasing in the last years. In this paper, we propose a network-based model for data analysis called a chronnet. The main goal of this model is to represent consecutive recurrent events between cells.
1
5
10
Mon Jun 12 2017
NLP
Attention Is All You Need
The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms. Experiments on two machine translation tasks show these models to be superior in
50
215
883
Mon Oct 30 2017
Machine Learning
Graph Attention Networks
Graph attention networks (GATs) are novel neural network architectures that operate on graph-structured data. GATs leverage masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions.
4
99
432
Thu Jan 03 2019
Machine Learning
A Comprehensive Survey on Graph Neural Networks
Deep learning has revolutionized many machine learning tasks in recent years. Data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data is generated from non-Euclidean domains.
4
3
15
Fri Sep 09 2016
Machine Learning
Semi-Supervised Classification with Graph Convolutional Networks
We present a scalable approach for semi-supervised learning on graph-structured data. The approach is based on an efficient variant of convolutional neural networks. We motivate the choice of our architecture via a localized first-order approximation of graph convolutions.
3
1
2
Fri Jun 22 2018
Neural Networks
Hierarchical Graph Representation Learning with Differentiable Pooling
DiffPool is a differentiable graph pooling module that can generate hierarchical representations of graphs. It can be combined with various graph neural network architectures in an end-to-end fashion. Combining existing GNN methods with DiffPool yields an average improvement of 5-10%
0
0
0
Thu Jun 30 2016
Machine Learning
Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
We are interested in generalizing convolutional neural networks from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks. We present a formulation of CNNs in the context of spectral graph theory.
0
0
0