Variational Gridded Graph Convolution Network for Node Classification

Hong, Xiaobin; Zhang, Tong; Cui, Zhen; Yang, Jian

doi:10.1109/jas.2021.1004201

Cited by 15 publications

(6 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the above equation, H (1) denotes the output of the first layer and the input of the second layer; H (2) denotes the output of the second layer; ReLU denotes the activation function; X denotes the input of the first layer neural network; W denotes the weight of the graph neural network; W (1) denotes the weight of the first layer neural network; W (2) denotes the weight of the second layer neural network. Â is a single-layer convolution operation, which can be interpreted as a convolution kernel, as shown in Equation (8).…”

Section: Graph Convolution Layermentioning

confidence: 99%

“…where H (2) is the input to the output layer and Z is the classification result of the model. Labelling the samples allows the graph convolution model to evaluate the corresponding cross-entropy loss function for semi-supervised node classification as a whole.…”

Section: Output Layermentioning

confidence: 99%

“…where H L is the index set with labelled nodes and the Adam [34] optimizer is used to train the neural network weights W (1) and W (2) by gradient descent. After a fixed number of model iterations, the softmax [35] normalization function is used to classify the convolutional results computed by the convolutional layer in order to derive the final labels of the nodes to be classified.…”

Section: Output Layermentioning

confidence: 99%

“…The development stages of graph neural networks have led to unprecedented progress in the learning of graph structure. One of the most common tasks is semi-supervised node classification [1,2], in which many nodes lack corresponding labels, and the labels of unlabeled nodes must therefore be determined using the topological complementary information of the nodes in the graph [3]. Social network analysis, protein interoperation network analysis, recommender systems, interdocument classification, and inter-paper classification [4] are just a few of the fields in which GCN's semi-supervised node classification has been widely applied.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

A Graph Neural Network Node Classification Application Model with Enhanced Node Association

Zhang

2023

Applied Sciences

View full text Add to dashboard Cite

This study combines the present stage of the node classification problem with the fact that there is frequent noise in the graph structure of the graph convolution calculation, which can lead to the omission of some of the actual edge relations between nodes and the appearance of numerous isolated nodes. In this paper, we propose the graph neural network model ENode-GAT for improving the accuracy of small sample node classification using the method of external referencing of similar word nodes, combined with Graph Convolutional Neural Network (GCN), Graph Attention Network (GAT), and the early stop algorithm. In order to demonstrate the applicability of the model, this paper employs two distinct types of node datasets for its investigations. The first is the Cora dataset, which is widely used in node classification at this time, and the second is a small-sample Stock dataset created by Eastern Fortune’s stock prospectus of the Science and Technology Board (STB). The experimental results demonstrate that the ENode-GAT model proposed in this paper obtains 85.1% classification accuracy on the Cora dataset and 85.3% classification accuracy on the Stock dataset, with certain classification advantages. It also verifies the future applicability of the model to the fields of stock classification, tender document classification, news classification, and government announcement classification, among others.

show abstract

Section: Graph Convolution Layermentioning

confidence: 99%

Section: Output Layermentioning

confidence: 99%

Section: Output Layermentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Graph Neural Network Node Classification Application Model with Enhanced Node Association

Zhang

2023

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Whereas, the skip-gram method predicts the surrounding words with central words, and the time complexity is O(KV), and the training time is longer than CBOW. The CBOW model training aims to maximize the probability of central word occurrence [11] . After the CBOW model training, the word vector matrix can be obtained, and this word vector matrix can be used as the input for deep learning.…”

Section: Word2vec Modelmentioning

confidence: 99%

Text sentiment classification based on Vit-BiGRU-attention model

Wang

2022

International Conference on Artificial Intelligence and Intelligent Information Processing (AIIIP 2022)

View full text Add to dashboard Cite

Nowadays, more and more users are playing an important role on the Internet. The more comments they post, the more information they contain and the more informative they are. In order to analyze the sentiment orientation of users' comments more accurately, the text Vit-BiGRU-Attention sentiment classification model is based on BiGRU and Attention mechanisms. First, the CBOW model is used to train the word vector. Second, BiGRU is combined with Viterbi algorithm to extract contextual features of the text by combining forward and backward hidden layers. Then, different weights are assigned to words by the attention mechanism to enhance the understanding of emotions and determine the polarity of emotions. Finally, the output is passed through a softmax classifier. The experimental results show that the accuracy of the model has been greatly improved.

show abstract

An integrated topic modeling and auto-encoder for semantic-rich network embedding and news recommendation

2023

Neural Comput & Applic

View full text Add to dashboard Cite

Variational Gridded Graph Convolution Network for Node Classification

Cited by 15 publications

References 36 publications

A Graph Neural Network Node Classification Application Model with Enhanced Node Association

A Graph Neural Network Node Classification Application Model with Enhanced Node Association

Text sentiment classification based on Vit-BiGRU-attention model

An integrated topic modeling and auto-encoder for semantic-rich network embedding and news recommendation

Contact Info

Product

Resources

About