Results 31 to 40 of about 36,148 (258)
Dual graph convolutional neural network for predicting chemical networks
BMC Bioinformatics, 2020 Background Predicting of chemical compounds is one of the fundamental tasks in bioinformatics and chemoinformatics, because it contributes to various applications in metabolic engineering and drug discovery.
Shonosuke Harada +6 more
doaj +1 more source
Graph Capsule Convolutional Neural Networks
CoRR, 2018 Graph Convolutional Neural Networks (GCNNs) are the most recent exciting advancement in deep learning field and their applications are quickly spreading in multi-cross-domains including bioinformatics, chemoinformatics, social networks, natural language processing and computer vision.
Saurabh Verma, Zhi-Li Zhang
openaire +2 more sources
Graph Based Convolutional Neural Network
CoRR, 2016 11 pages, accepted into BMVC ...
Michael Edwards, Xianghua Xie
openaire +2 more sources
Human Action Recognition Algorithm Based on Adaptive Shifted Graph Convolutional NeuralNetwork with 3D Skeleton Similarity [PDF]
Jisuanji kexueGraph convolutional neural network(GCN) has achieved good results in the field of human action recognition based on 3D skeleton.However,in most of the existing GCN methods,the construction of the behavior diagram is based on the manual setting of the ...
YAN Wenjie, YIN Yiying
doaj +1 more source
Tensor graph convolutional neural network
CoRR, 2018 In this paper, we propose a novel tensor graph convolutional neural network (TGCNN) to conduct convolution on factorizable graphs, for which here two types of problems are focused, one is sequential dynamic graphs and the other is cross-attribute graphs.
Tong Zhang 0021 +3 more
openaire +2 more sources
Kernel Graph Convolutional Neural Networks [PDF]
, 2018 Graph kernels have been successfully applied to many graph classification problems. Typically, a kernel is first designed, and then an SVM classifier is trained based on the features defined implicitly by this kernel. This two-stage approach decouples data representation from learning, which is suboptimal.
Giannis Nikolentzos +4 more
openaire +2 more sources
Stability of graph convolutional neural networks to stochastic perturbations [PDF]
Signal Processing, 2021 Graph convolutional neural networks (GCNNs) are nonlinear processing tools to learn representations from network data. A key property of GCNNs is their stability to graph perturbations. Current analysis considers deterministic perturbations but fails to provide relevant insights when topological changes are random. This paper investigates the stability
Zhan Gao, Elvin Isufi, Alejandro Ribeiro
openaire +2 more sources
Learning Convolutional Neural Networks for Graphs
CoRR, 2016 To be presented at ICML ...
Mathias Niepert +2 more
openaire +3 more sources
Graph convolutional neural networks via scattering
Applied and Computational Harmonic Analysis, 2020 26 pages, 9 figures, 4 ...
Dongmian Zou, Gilad Lerman
openaire +4 more sources
Stability and Generalization of Graph Convolutional Neural Networks [PDF]
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, 2019 Inspired by convolutional neural networks on 1D and 2D data, graph convolutional neural networks (GCNNs) have been developed for various learning tasks on graph data, and have shown superior performance on real-world datasets. Despite their success, there is a dearth of theoretical explorations of GCNN models such as their generalization properties. In
Saurabh Verma, Zhi-Li Zhang
openaire +2 more sources