Filters








6,658 Hits in 5.7 sec

Learning Vertex Convolutional Networks for Graph Classification [article]

Lu Bai, Lixin Cui, Shu Wu, Yuhang Jiao, Edwin R. Hancock
2019 arXiv   pre-print
In this paper, we develop a new aligned vertex convolutional network model to learn multi-scale local-level vertex features for graph classification.  ...  Our idea is to transform the graphs of arbitrary sizes into fixed-sized aligned vertex grid structures, and define a new vertex convolution operation by adopting a set of fixed-sized one-dimensional convolution  ...  Learning Vertex Convolutional Networks In this section, we develop a new vertex convolutional network model for graph classification.  ... 
arXiv:1902.09936v1 fatcat:iib4dt3qurecxkcefwtvgvayl4

Graph Convolutional Neural Networks based on Quantum Vertex Saliency [article]

Lu Bai, Yuhang Jiao, Luca Rossi, Lixin Cui, Jian Cheng, Edwin R. Hancock
2019 arXiv   pre-print
This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes.  ...  the graph representation and learning in the quantum spatial graph convolution layer and the traditional convolutional layer for graph classifications.  ...  This paper aims to develop a new graph convolutional neural network using quantum vertex saliency, for the purpose of graph classification.  ... 
arXiv:1809.01090v2 fatcat:t4snzjrdwrh6nikekskkndv3he

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification [article]

Lu Bail, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock
2019 arXiv   pre-print
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification.  ...  We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models  ...  The aim of this paper is to develop a new Graph Convolutional Network (GCN) model to learn effective features for graph classification.  ... 
arXiv:1904.04238v2 fatcat:qextujhehjarfkllqqqtoqm4ou

Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification

Lu Bai, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin Hancock
2020 IEEE Transactions on Pattern Analysis and Machine Intelligence  
In this paper, we develop a novel Backtrackless Aligned-Spatial Graph Convolutional Network (BASGCN) model to learn effective features for graph classification.  ...  We show that the proposed BASGCN model not only reduces the problems of information loss and imprecise information representation arising in existing spatially-based Graph Convolutional Network (GCN) models  ...  ACKNOWLEDGMENTS This work is supported by the National Natural Science Foundation of China (Grant no. 61976235 and 61602535), the program for innovation research in Central University of Finance and Economics  ... 
doi:10.1109/tpami.2020.3011866 pmid:32750832 fatcat:rqroqwb2njdtxkl2c4bocaxdxy

Robust Spatial Filtering With Graph Convolutional Neural Networks

Felipe Petroski Such, Shagan Sah, Miguel Alexander Dominguez, Suhas Pillai, Chao Zhang, Andrew Michael, Nathan D. Cahill, Raymond Ptucha
2017 IEEE Journal on Selected Topics in Signal Processing  
Convolutional Neural Networks (CNNs) have recently led to incredible breakthroughs on a variety of pattern recognition problems.  ...  Graph-CNNs can handle both heterogeneous and homogeneous graph data, including graphs having entirely different vertex or edge sets.  ...  This technique is used for semi-supervised document classification Figure 2 : General vertex-edge domain Graph-CNN architecture. Convolution and pooling layers are cascaded into a deep network.  ... 
doi:10.1109/jstsp.2017.2726981 fatcat:sj2bq77u2faateg3nnnl75sewu

Affinity-Point Graph Convolutional Network for 3D Point Cloud Analysis

Yang Wang, Shunping Xiao
2022 Applied Sciences  
In this paper, an Affinity-Point Graph Convolutional Network (AP-GCN) is proposed to learn the graph structure for each reference point.  ...  In recent years, convolutional neural networks have achieved great success in 2D image representation learning.  ...  For the segmentation task, the main structure is the same as the classification network.  ... 
doi:10.3390/app12115328 fatcat:wvon3csv4farhom67j6tlixcaa

PiNet: Attention Pooling for Graph Classification [article]

Peter Meltzer, Marcelo Daniel Gutierrez Mallea, Peter J. Bentley
2020 arXiv   pre-print
We propose PiNet, a generalised differentiable attention-based pooling mechanism for utilising graph convolution operations for graph level classification.  ...  We demonstrate high sample efficiency and superior performance over other graph neural networks in distinguishing isomorphic graph classes, as well as competitive results with state of the art methods  ...  (http://braintree.com) for providing the full funding for this research.  ... 
arXiv:2008.04575v1 fatcat:gdavrz7xf5f6pguok3fll5xhfy

MG-SAGC: A multiscale graph and its self-adaptive graph convolution network for 3D point clouds [article]

Bo Wu, Bo Lang
2020 arXiv   pre-print
Because traditional convolutional neural networks are not applicable to graph data with irregular vertex neighborhoods, this paper presents an sef-adaptive graph convolution kernel that uses the Chebyshev  ...  First, we propose a multiscale graph generation method for point clouds.  ...  Finally, the global feature is input to the MLP and a softmax layer is used for classification. Figure 4 : 4 Network framework of point cloud classification based on adaptive graph convolution.  ... 
arXiv:2012.12445v1 fatcat:f52sq7ikljbypel7mtv2zcofei

A Practical Tutorial on Graph Neural Networks [article]

Isaac Ronald Ward, Jack Joyner, Casey Lickfold, Yulan Guo, Mohammed Bennamoun
2021 arXiv   pre-print
deep learning techniques.  ...  Graph neural networks (GNNs) have recently grown in popularity in the field of artificial intelligence (AI) due to their unique ability to ingest relatively unstructured data types as input data.  ...  ACKNOWLEDGMENTS We thank our colleague Richard Pienaar for providing feedback which greatly improved this work.  ... 
arXiv:2010.05234v3 fatcat:vubypxjlnfaspp4mfvq7bhcuou

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs

Martin Simonovsky, Nikos Komodakis
2017 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)  
Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification.  ...  learning approaches.  ...  We gratefully acknowledge NVIDIA Corporation for the donated GPU used in this research. We are thankful to anonymous reviewers for their feedback.  ... 
doi:10.1109/cvpr.2017.11 dblp:conf/cvpr/SimonovskyK17 fatcat:ub6guqyufbhmfintvcc25z5kky

Dynamic Hypergraph Neural Networks

Jianwen Jiang, Yuxuan Wei, Yifan Feng, Jingxuan Cao, Yue Gao
2019 Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence  
In recent years, graph/hypergraph-based deep learning methods have attracted much attention from researchers.  ...  The HGC module includes two phases: vertex convolution and hyperedge convolution, which are designed to aggregate feature among vertices and hyperedges, respectively.  ...  For data with inherent graph structure, we conducted an experiment on a citation network benchmark, the Cora dataset [Sen et al., 2008] , for the node classification task.  ... 
doi:10.24963/ijcai.2019/366 dblp:conf/ijcai/JiangWFCG19 fatcat:34b2v7aka5dibb46vwah6dmviu

Hypergraph Convolution and Hypergraph Attention [article]

Song Bai, Feihu Zhang, Philip H.S. Torr
2020 arXiv   pre-print
To efficiently learn deep embeddings on the high-order graph-structured data, we introduce two end-to-end trainable operators to the family of graph neural networks, i.e., hypergraph convolution and hypergraph  ...  Extensive experimental results with semi-supervised node classification demonstrate the effectiveness of hypergraph convolution and hypergraph attention.  ...  each vertex can be propagated in a graph neural network.  ... 
arXiv:1901.08150v2 fatcat:gqanvg6tqrhchlx2dlub5iosgu

Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning [article]

Qimai Li, Zhichao Han, Xiao-Ming Wu
2018 arXiv   pre-print
For graph-based semisupervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers  ...  Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation.  ...  The authors would like to thank the reviewers for their insightful comments and useful discussions.  ... 
arXiv:1801.07606v1 fatcat:jeuaoipf7zhp5gp5bjdfppusiq

Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning

Qimai Li, Zhichao Han, Xiao-ming Wu
2018 PROCEEDINGS OF THE THIRTIETH AAAI CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE TWENTY-EIGHTH INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE CONFERENCE  
For graph-based semi-supervised learning, a recent important development is graph convolutional networks (GCNs), which nicely integrate local vertex features and graph topology in the convolutional layers  ...  Our approaches significantly improve GCNs in learning with very few labels, and exempt them from requiring additional labels for validation.  ...  The authors would like to thank the reviewers for their insightful comments and useful discussions.  ... 
doi:10.1609/aaai.v32i1.11604 fatcat:cfaq4vntibbgvb6zey3zwvil34

Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs [article]

Martin Simonovsky, Nikos Komodakis
2017 arXiv   pre-print
Together with the proper choice of graph coarsening, we explore constructing deep neural networks for graph classification.  ...  learning approaches.  ...  We gratefully acknowledge NVIDIA Corporation for the donated GPU used in this research. We are thankful to anonymous reviewers for their feedback.  ... 
arXiv:1704.02901v3 fatcat:lnnaj2x6trcabpnve2onjj7o7q
« Previous Showing results 1 — 15 out of 6,658 results