Results 41 to 50 of about 142,397 (310)
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
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
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
Learning Convolutional Neural Networks for Graphs
CoRR, 2016 To be presented at ICML ...
Mathias Niepert +2 more
openaire +3 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
Graph Based Convolutional Neural Network
CoRR, 2016 11 pages, accepted into BMVC ...
Michael Edwards, Xianghua Xie
openaire +2 more sources
Machine Learning and Knowledge Extraction, 2020 This paper explores the value of weak-ties in classifying academic literature with the use of graph convolutional neural networks. Our experiments look at the results of treating weak-ties as if they were strong-ties to determine if that assumption ...
Neda H. Bidoki +2 more
doaj +1 more source
Graph learning-based spatial-temporal graph convolutional neural networks for traffic forecasting
Connection Science, 2022 Traffic forecasting is highly challenging due to its complex spatial and temporal dependencies in the traffic network. Graph Convolutional Neural Network (GCN) has been effectively used for traffic forecasting due to its excellent performance in ...
Na Hu +4 more
doaj +1 more source
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
Convolution Based Graph Representation Learning from the Perspective of High Order Node Similarities
Mathematics, 2022 Nowadays, graph representation learning methods, in particular graph neural network methods, have attracted great attention and performed well in many downstream tasks. However, most graph neural network methods have a single perspective since they start
Xing Li +3 more
doaj +1 more source