Results 1 to 10 of about 38,896 (265)
Node-Feature Convolution for Graph Convolutional Networks [PDF]
Pattern Recognition, 2022 Graph convolutional network (GCN) is an effective neural network model for graph representation learning. However, standard GCN suffers from three main limitations: (1) most real-world graphs have no regular connectivity and node degrees can range from one to hundreds or thousands, (2) neighboring nodes are aggregated with fixed weights, and (3) node ...
Zhang, L., Song, H., Aletras, N., Lu, H.
openaire +2 more sources
Review of Text Classification Methods Based on Graph Convolutional Network [PDF]
Jisuanji kexue, 2022 Text classification is a common task in natural language processing,in which there are a lot of research and progress based on machine learning and deep learning.However,these traditional methods can only process Euclidean spatial data,and cannot express
TAN Ying-ying, WANG Jun-li, ZHANG Chao-bo
doaj +1 more source
Aspect-level Sentiment Analysis Integrating Syntactic Distance and Aspect-attention [PDF]
Jisuanji kexue, 2023 Currently,the over-smoothing problem arises from deep convolution in syntactic dependency tree-based graph convolutional networks.This problem prevents the convolutional graph network from extracting the global node information of the syntactic ...
ZHANG Longji, ZHAO Hui
doaj +1 more source
Dynamic graph convolutional networks [PDF]
Pattern Recognition, 2020 Many different classification tasks need to manage structured data, which are usually modeled as graphs. Moreover, these graphs can be dynamic, meaning that the vertices/edges of each graph may change during time. Our goal is to jointly exploit structured data and temporal information through the use of a neural network model.
Franco Manessi +2 more
openaire +2 more sources
SPATIOTEMPORAL GRAPH CONVOLUTIONAL NEURAL NETWORKS FOR METRO FLOW PREDICTION [PDF]
The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2022 Forecasting urban metro flow accurately plays an important role for station management and passenger safety. Owing to the limitations of non-linearity and complexity of traffic flow data, traditional methods cannot satisfy the requirements of effectively
S. Jin, C. Jing, Y. Wang, X. Lv
doaj +1 more source
Applied Sciences, 2022 Graph convolutional neural networks (GCNNs) have been successfully applied to a wide range of problems, including low-dimensional Euclidean structural domains representing images, videos, and speech and high-dimensional non-Euclidean domains, such as ...
Ji-Hun Bae +6 more
doaj +1 more source
Deformable Graph Convolutional Networks
Proceedings of the AAAI Conference on Artificial Intelligence, 2022 Graph neural networks (GNNs) have significantly improved the representation power for graph-structured data. Despite of the recent success of GNNs, the graph convolution in most GNNs have two limitations. Since the graph convolution is performed in a small local neighborhood on the input graph, it is inherently incapable to capture long-range ...
Jinyoung Park 0005 +3 more
openaire +2 more sources
Graph-Revised Convolutional Network [PDF]
, 2021 Graph Convolutional Networks (GCNs) have received increasing attention in the machine learning community for effectively leveraging both the content features of nodes and the linkage patterns across graphs in various applications. As real-world graphs are often incomplete and noisy, treating them as ground-truth information, which is a common practice ...
Donghan Yu +4 more
openaire +2 more sources
Graph convolutional network for fMRI analysis based on connectivity neighborhood
Network Neuroscience, 2021 There have been successful applications of deep learning to functional magnetic resonance imaging (fMRI), where fMRI data were mostly considered to be structured grids, and spatial features from Euclidean neighbors were usually extracted by the ...
Lebo Wang, Kaiming Li, Xiaoping P. Hu
doaj +1 more source
Lorentzian Graph Convolutional Networks [PDF]
Proceedings of the Web Conference 2021, 2021 Les réseaux convolutionnels de graphes (GCN) ont récemment fait l'objet d'une attention considérable de la part de la recherche. La plupart des GCN apprennent les représentations de nœuds en géométrie euclidienne, mais cela pourrait avoir une distorsion élevée dans le cas de l'intégration de graphes avec une structure sans échelle ou hiérarchique ...
Yiding Zhang +4 more
openaire +2 more sources