Structured Sequence Modeling with Graph Convolutional Recurrent Networks

Seo, Youngjoo; Defferrard, Michaël; Bresson, Xavier

doi:10.48550/arxiv.1612.07659

Cited by 24 publications

(35 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Post-GCNN representation, LSTM-RNNs have been used to analyze time-series data structured over a graph. Seo et al (2016) propose a model which combines GCNN and RNN to predict moving MNIST data. Liang et al (2016) design a graph LSTM for semantic object parsing in images.…”

Section: Discussionmentioning

confidence: 99%

Graph2Seq: Scalable Learning Dynamics for Graphs

Venkatakrishnan¹,

Alizadeh²,

Viswanath³

2018

Preprint

View full text Add to dashboard Cite

Neural networks have been shown to be an effective tool for learning algorithms over graph-structured data. However, graph representation techniques-that convert graphs to real-valued vectors for use with neural networks-are still in their infancy. Recent works have proposed several approaches (e.g., graph convolutional networks), but these methods have difficulty scaling and generalizing to graphs with different sizes and shapes. We present GRAPH2SEQ, a new technique that represents vertices of graphs as infinite time-series. By not limiting the representation to a fixed dimension, GRAPH2SEQ scales naturally to graphs of arbitrary sizes and shapes. GRAPH2SEQ is also reversible, allowing full recovery of the graph structure from the sequences. By analyzing a formal computational model for graph representation, we show that an unbounded sequence is necessary for scalability. Our experimental results with GRAPH2SEQ show strong generalization and new state-of-the-art performance on a variety of graph combinatorial optimization problems.

show abstract

Section: Discussionmentioning

confidence: 99%

Graph2Seq: Scalable Learning Dynamics for Graphs

Venkatakrishnan¹,

Alizadeh²,

Viswanath³

2018

Preprint

View full text Add to dashboard Cite

show abstract

“…Structured RNN [10] attempts to fit the spatio-temporal graph into a mixture of recurrent neural networks by associating each node and edge to a certain type of the networks. Based on the framework of convLSTM [22], graph convolutional recurrent network (GCRN) [19] is firstly proposed modeling structured sequences by replacing regular 2D convolution with spectral-based graph convolution.…”

Section: Related Workmentioning

confidence: 99%

“…Inside each recurrent unit, convolutional operations with kernels are substituted for multiplications by dense matrices, which enables the network for handling image sequences. Afterwards, [19] extends this approach by replacing the standard convolution by the graph convolution for structured sequence modeling. Following the similar scheme, we Algorithm 1: Graph Partition Algorithm (gPartition)…”

Section: Spatial Graph Poolingmentioning

confidence: 99%

“…It consists of 20-frame sequences (first 10 frames as input and the last for prediction), each of which contains two handwritten digits whose location is bouncing inside a 64 × 64 patch. 1 Following the default setup in [19], image frames are converted into spatio-temporal graphs. The adjacency matrix is constructed based on distances between each pixel node and its equal neighbors of a k-nearest-neighbor graph in four directions (up, down, left and right).…”

Section: Spatio-temporal Sequence Modeling On Moving-mnistmentioning

confidence: 99%

See 1 more Smart Citation

ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling

Yu,

Yin,

Zhu

2019

Preprint

View full text Add to dashboard Cite

The spatio-temporal graph learning is becoming an increasingly important object of graph study. Many application domains involve highly dynamic graphs where temporal information is crucial, e.g. traffic networks and financial transaction graphs. Despite the constant progress made on learning structured data, there is still a lack of effective means to extract dynamic complex features from spatio-temporal structures. Particularly, conventional models such as convolutional networks or recurrent neural networks are incapable of revealing the temporal patterns in short or long terms and exploring the spatial properties in local or global scope from spatiotemporal graphs simultaneously. To tackle this problem, we design a novel multi-scale architecture, Spatio-Temporal U-Net (ST-UNet), for graph-structured time series modeling. In this U-shaped network, a paired sampling operation is proposed in spacetime domain accordingly: the pooling (ST-Pool) coarsens the input graph in spatial from its deterministic partition while abstracts multi-resolution temporal dependencies through dilated recurrent skip connections; based on previous settings in the downsampling, the unpooling (ST-Unpool) restores the original structure of spatio-temporal graphs and resumes regular intervals within graph sequences. Experiments on spatio-temporal prediction tasks demonstrate that our model effectively captures comprehensive features in multiple scales and achieves substantial improvements over mainstream methods on several real-world datasets.

show abstract

“…It has played important roles in climate studies, market analysis, traffic control, and energy grid management (Makridakis et al, 1997) and has inspired the development of various predictive models that capture the temporal dynamics of the underlying system. These models range from early autoregressive approaches (Hamilton, 1994;Asteriou & Hall, 2011) to the recent deep learning methods (Seo et al, 2016;Zhao et al, 2019).…”

Section: Introductionmentioning

confidence: 99%

Discrete Graph Structure Learning for Forecasting Multiple Time Series

Shang,

Chen,

2021

Preprint

View full text Add to dashboard Cite

Time series forecasting is an extensively studied subject in statistics, economics, and computer science. Exploration of the correlation and causation among the variables in a multivariate time series shows promise in enhancing the performance of a time series model. When using deep neural networks as forecasting models, we hypothesize that exploiting the pairwise information among multiple (multivariate) time series also improves their forecast. If an explicit graph structure is known, graph neural networks (GNNs) have been demonstrated as powerful tools to exploit the structure. In this work, we propose learning the structure simultaneously with the GNN if the graph is unknown. We cast the problem as learning a probabilistic graph model through optimizing the mean performance over the graph distribution. The distribution is parameterized by a neural network so that discrete graphs can be sampled differentiably through reparameterization. Empirical evaluations show that our method is simpler, more efficient, and better performing than a recently proposed bilevel learning approach for graph structure learning, as well as a broad array of forecasting models, either deep or non-deep learning based, and graph or non-graph based.

show abstract

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

Cited by 24 publications

References 5 publications

Graph2Seq: Scalable Learning Dynamics for Graphs

Graph2Seq: Scalable Learning Dynamics for Graphs

ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling

Discrete Graph Structure Learning for Forecasting Multiple Time Series

Contact Info

Product

Resources

About