Classification with Vertex-Based Graph Convolutional Neural Networks

Shi, John; Cheung, Mark; Du, Ji-Xiang; Jose, M F Moura

doi:10.1109/acssc.2018.8645378

Cited by 8 publications

(5 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This is consistent with the concept of convolution in graph signal processing [2]. TAGCN designs a set of fixed-size learnable filters whose topologies are adaptive to the topology of the graph as the filters scan the graph to perform convolution, see also [8], [9]. Other implementations, such as GraphSAGE [10] and graph attention networks (GATs) [11], are also defined directly in the vertex domain of the graph and apply a learned, convolutionlike aggregation function.…”

Section: Introductionsupporting

confidence: 68%

See 1 more Smart Citation

Pooling in Graph Convolutional Neural Networks

Cheung

Shi

Jiang

et al. 2019

2019 53rd Asilomar Conference on Signals, Systems, and Computers

Self Cite

View full text Add to dashboard Cite

Graph convolutional neural networks (GCNNs) are a powerful extension of deep learning techniques to graphstructured data problems. We empirically evaluate several pooling methods for GCNNs, and combinations of those graph pooling methods with three different architectures: GCN, TAGCN, and GraphSAGE. We confirm that graph pooling, especially DiffPool, improves classification accuracy on popular graph classification datasets and find that, on average, TAGCN achieves comparable or better accuracy than GCN and GraphSAGE, particularly for datasets with larger and sparser graph structures.

show abstract

Section: Introductionsupporting

confidence: 68%

“…We concentrate on three implementations of GCNNs, derived from different definitions of graph convolution: graph convolutional networks (GCNs) [6], GraphSAGE [10], and topology-adaptive graph convolutional networks (TAGCNs) [7], [9].…”

Section: A Graph Convolutional Layermentioning

confidence: 99%

Pooling in Graph Convolutional Neural Networks

Cheung

Shi

Jiang

et al. 2019

2019 53rd Asilomar Conference on Signals, Systems, and Computers

Self Cite

View full text Add to dashboard Cite

show abstract

“…As a variant of GCN, Topology adaptive graph convolutional networks (TAGCN) avoids the eigen decomposition [21], but calculates the coefficients of the adjacency matrix [22], reducing the computational complexity. In addition, TAGCN uses a set of filters of size-1 to size-K to extract the features in each convolutional layer.…”

Section: Tagcnmentioning

confidence: 99%

GLSTM-DTA: Application of Prediction Improvement Model Based on GNN and LSTM

Liang

Jiang

Min

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Most prediction models of drug-target binding affinity (DTA) treated drugs and targets as sequences, and feature extraction networks could not sufficiently extract features. Inspired by DeepDTA and GraphDTA, we proposed an improved model named GLSTM-DTA for DTA prediction, which combined Graph Neural Network (GNN) and Long Short-Term Memory Network (LSTM). The feature extraction block consists of two parts: GNN block and LSTM block, which extract drug features and protein features respectively. The novelty of our work is using LSTM, instead of Convolutional neural network (CNN) to extract protein sequence features, which is facilitating to capture long-term dependencies in sequence. In addition, we also converted drugs into graph structures and use GNN for feature extraction. The improved model performs better than DeepDTA and GraphDTA. The comprehensive results prove the advantages of our model in accurately predicting the binding affinity of drug-targets.

show abstract

“…Spectral domain approach [31]: The absence of graph translation invariance poses difficulties in defining convolutional neural networks in the nodal domain. The spectral domain approach uses the convolution theorem to define the graph convolution from the spectral domain.…”

Section: Spectral Domain-based Graph Convolution Network (Sgc)mentioning

confidence: 99%

Prediction of Large Scale Spatio-temporal Traffic Flow Data with New Graph Convolution Model

Wang¹,

Shi²,

He³

et al. 2022

Intelligent Electronics and Circuits - Terahertz, ITS, and Beyond

View full text Add to dashboard Cite

Prompt and accurate prediction of traffic flow is quite useful. It will help traffic administrator to analyze the road occupancy status and formulate dynamic and flexible traffic control in advance to improve the road capacity. It can also provide more precise navigation guidance for the road users in future. However, it is hard to predict spatiotemporal traffic flow data in large scale promptly with high accuracy caused by complex interrelation and nonlinear dynamic nature. With development of deep learning and other technologies, many prediction networks could predict traffic flow with accumulated historical data in time series. In consideration of the regional characteristics of traffic flow, the emerging Graph Convolutional Network (GCN) model is systematically introduced with representative applications. Those successful applications provide a possible way to contribute fast and proper traffic control strategies that could relieve traffic pressure, reduce potential conflict, fasten emergency response, etc.

show abstract

Classification with Vertex-Based Graph Convolutional Neural Networks

Cited by 8 publications

References 5 publications

Pooling in Graph Convolutional Neural Networks

Pooling in Graph Convolutional Neural Networks

GLSTM-DTA: Application of Prediction Improvement Model Based on GNN and LSTM

Prediction of Large Scale Spatio-temporal Traffic Flow Data with New Graph Convolution Model

Contact Info

Product

Resources

About