Results 41 to 50 of about 5,811,866 (292)

Pseudo-Riemannian Graph Convolutional Networks [PDF]

open access: yesAdvances in Neural Information Processing Systems 35, 2022
Graph convolutional networks (GCNs) are powerful frameworks for learning embeddings of graph-structured data. GCNs are traditionally studied through the lens of Euclidean geometry. Recent works find that non-Euclidean Riemannian manifolds provide specific inductive biases for embedding hierarchical or spherical data.
Xiong, Bo   +5 more
openaire   +4 more sources

Superpixel Spectral–Spatial Feature Fusion Graph Convolution Network for Hyperspectral Image Classification

open access: yes, 2022
Recently, convolutional neural networks (CNNs) have demonstrated impressive capabilities in the representation and classification of hyperspectral remote sensing images. Traditional CNNs require massive data to sufficiently train the network.
Lijuan Duan   +11 more
core   +1 more source

Factorizable Graph Convolutional Networks

open access: yesCoRR, 2020
Graphs have been widely adopted to denote structural connections between entities. The relations are in many cases heterogeneous, but entangled together and denoted merely as a single edge between a pair of nodes. For example, in a social network graph, users in different latent relationships like friends and colleagues, are usually connected via a ...
Yiding Yang   +3 more
openaire   +4 more sources

Distributed Training of Graph Convolutional Networks [PDF]

open access: yesIEEE Transactions on Signal and Information Processing over Networks, 2021
Published on IEEE Transactions on Signal and Information Processing over ...
Scardapane S, Spinelli I, Di Lorenzo P
openaire   +2 more sources

AN EFFECTIVE FOVEATED 360° IMAGE ASSESSMENT BASED ON GRAPH CONVOLUTION NETWORK

open access: yes, 2022
Non-uniform (foveated) 360° image quality assessment using graph convolution ...
Ha Do Thu (12056375)   +7 more
core   +1 more source

Dynamic Multi-Graph Convolution-Based Channel-Weighted Transformer Feature Fusion Network for Epileptic Seizure Prediction

open access: yesIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2023
Electroencephalogram (EEG) based seizure prediction plays an important role in the closed-loop neuromodulation system. However, most existing seizure prediction methods based on graph convolution network only focused on constructing the static graph ...
Yifan Wang   +5 more
doaj   +1 more source

Directed Graph Convolutional Network

open access: yesCoRR, 2020
Graph Convolutional Networks (GCNs) have been widely used due to their outstanding performance in processing graph-structured data. However, the undirected graphs limit their application scope. In this paper, we extend spectral-based graph convolution to directed graphs by using first- and second-order proximity, which can not only retain the ...
Zekun Tong   +4 more
openaire   +2 more sources

Multi-omics Cancer Prognosis Analysis Based on Graph Convolution Network

open access: yes, 2021
Cancer survival analysis is important for patients' follow-up treatment, and accurate prediction is conductive to improving the survival rate of patients.
Yi Wang   +7 more
core   +1 more source

Atrial Fibrillation Detection Algorithm Based on Graph Convolution Network

open access: yesIEEE Access, 2023
Atrial fibrillation (AF) is a common type of arrhythmia with a high incidence and risk, and it is difficult to monitor. Deep learning-based algorithms for AF detection have made preliminary progress, with Recurrent Convolution Neural Networks (RCNN ...
Hua Ma, Lingnan Xia
doaj   +1 more source

Convolutional Graph Neural Networks

open access: yes2019 53rd Asilomar Conference on Signals, Systems, and Computers, 2019
Convolutional neural networks (CNNs) restrict the, otherwise arbitrary, linear operation of neural networks to be a convolution with a bank of learned filters. This makes them suitable for learning tasks based on data that exhibit the regular structure of time signals and images.
Fernando Gama   +3 more
openaire   +4 more sources

Home - About - Disclaimer - Privacy