Structured Sequence Modeling with Graph Convolutional Recurrent Networks

Seo, Youngjoo; Defferrard, Michaël; Vandergheynst, Pierre; Bresson, Xavier

doi:10.1007/978-3-030-04167-0_33

Cited by 549 publications

(377 citation statements)

References 20 publications

Supporting

Mentioning

343

Contrasting

Order By: Relevance

“…where Gconv(·) is a graph convolutional layer. Graph Convolutional Recurrent Network (GCRN) [71] combines a LSTM network with ChebNet [21]. Diffusion Convolutional Recurrent Neural Network (DCRNN) [72] incorporates a proposed diffusion graph convolutional layer (Equation 18) into a GRU network.…”

Section: Spatial-temporal Graph Neural Networkmentioning

confidence: 99%

A Comprehensive Survey on Graph Neural Networks

Pan

Chen

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

6,328

2,977

View full text Add to dashboard Cite

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.

show abstract

Section: Spatial-temporal Graph Neural Networkmentioning

confidence: 99%

A Comprehensive Survey on Graph Neural Networks

Pan

Chen

et al. 2021

IEEE Trans. Neural Netw. Learning Syst.

6,328

2,977

View full text Add to dashboard Cite

show abstract

“…Simonovsky et al [23] formulate a convolution-like operation on graph signals performed in the spatial domain and are the first to apply graph convolutions to point cloud classification. In order to capture the spatial-temporal features of graph sequences, a graph convolutional LSTM is firstly proposed in [20], which is an extension of GCNs to have the recurrent architecture. Inspired by [20], we exploit a novel AGC-LSTM network to learn inherent spatiotemporal representations from skeleton sequences.…”

Section: Related Workmentioning

confidence: 99%

“…In order to capture the spatial-temporal features of graph sequences, a graph convolutional LSTM is firstly proposed in [20], which is an extension of GCNs to have the recurrent architecture. Inspired by [20], we exploit a novel AGC-LSTM network to learn inherent spatiotemporal representations from skeleton sequences.…”

Section: Related Workmentioning

confidence: 99%

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition

Chen

Wang

et al. 2019

2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

745

427

View full text Add to dashboard Cite

Skeleton-based action recognition is an important task that requires the adequate understanding of movement characteristics of a human action from the given skeleton sequence. Recent studies have shown that exploring spatial and temporal features of the skeleton sequence is vital for this task. Nevertheless, how to effectively extract discriminative spatial and temporal features is still a challenging problem. In this paper, we propose a novel Attention Enhanced Graph Convolutional LSTM Network (AGC-LSTM) for human action recognition from skeleton data. The proposed AGC-LSTM can not only capture discriminative features in spatial configuration and temporal dynamics but also explore the co-occurrence relationship between spatial and temporal domains. We also present a temporal hierarchical architecture to increase temporal receptive fields of the top AGC-LSTM layer, which boosts the ability to learn the high-level semantic representation and significantly reduces the computation cost. Furthermore, to select discriminative spatial information, the attention mechanism is employed to enhance information of key joints in each AGC-LSTM layer. Experimental results on two datasets are provided: NTU RGB+D dataset and Northwestern-UCLA dataset. The comparison results demonstrate the effectiveness of our approach and show that our approach outperforms the state-of-the-art methods on both datasets.

show abstract

“…In this paper, we use a deep learning based prediction model that leverages graph convolutions to incorporate spatial-temporal features of multiple data sources acquired in networks, and characterizes of roadway networks related to parking cruising time. Previous research related to our methodology include structural-RNN (Jain et al, 2016) and Graph-based convolutional recurrent network (Seo et al, 2016).…”

Section: Literature Reviewmentioning

confidence: 99%

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

Yang

et al. 2019

Transportation Research Part C: Emerging Technologies

166

View full text Add to dashboard Cite

A deep learning model is applied for predicting block-level parking occupancy in real time. The model leverages Graph-Convolutional Neural Networks (GCNN) to extract the spatial relations of traffic flow in large-scale networks, and utilizes Recurrent Neural Networks (RNN) with Long-Short Term Memory (LSTM) to capture the temporal features. In addition, the model is capable of taking multiple heterogeneously structured traffic data sources as input, such as parking meter transactions, traffic speed, and weather conditions. The model performance is evaluated through a case study in Pittsburgh downtown area. The proposed model outperforms other baseline methods including multi-layer LSTM and Lasso with an average testing MAPE of 10.6% when predicting block-level parking occupancies 30 minutes in advance. The case study also shows that, in generally, the prediction model works better for business areas than for recreational locations. We found that incorporating traffic speed and weather information can significantly improve the prediction performance. Weather data is particularly useful for improving predicting accuracy in recreational areas.

show abstract

Structured Sequence Modeling with Graph Convolutional Recurrent Networks

Cited by 549 publications

References 20 publications

A Comprehensive Survey on Graph Neural Networks

A Comprehensive Survey on Graph Neural Networks

An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition

A deep learning approach to real-time parking occupancy prediction in transportation networks incorporating multiple spatio-temporal data sources

Contact Info

Product

Resources

About