Hierarchical attention network for attributed community detection of joint representation

Zhao, Qiqi; Ma, Huifang; Guo, Lijun; Li, Zhixin

doi:10.1007/s00521-021-06723-y

Cited by 10 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…GAT: It is based on masked self-attentional layers. It avoids expensive matrix operations due to nodes in a neighborhood having varying weights, which can contribute to surrounding node feature extraction (Veličković et al , 2018; Zhao et al , 2022). Equation 6 indicates the significance between two nodes.GUCD: The encoder incorporate MRFasGCN method in the autoencoder framework that utilized the network and node semantics at the same time.…”

Section: Methodsmentioning

confidence: 99%

“…The goal is to figure out each node's underlying representation by looking at its neighbors. In the GCN layer's fundamental aggregation function, the attention coefficients in the graph attention network (GAT) layer allow each node to be given a unique weight (Veličković et al, 2018;Zhao et al, 2022). Detecting overlapping communities in complex networks is another significant aspect of community detection.…”

Section: Deep Learning-based Community Detectionmentioning

confidence: 99%

See 1 more Smart Citation

CommunityGCN: community detection using node classification with graph convolution network

Bhattacharya

Nagwani²,

Tripathi³

2023

DTA

View full text Add to dashboard Cite

PurposeA community demonstrates the unique qualities and relationships between its members that distinguish it from other communities within a network. Network analysis relies heavily on community detection. Despite the traditional spectral clustering and statistical inference methods, deep learning techniques for community detection have grown in popularity due to their ease of processing high-dimensional network data. Graph convolutional neural networks (GCNNs) have received much attention recently and have developed into a potential and ubiquitous method for directly detecting communities on graphs. Inspired by the promising results of graph convolutional networks (GCNs) in analyzing graph structure data, a novel community graph convolutional network (CommunityGCN) as a semi-supervised node classification model has been proposed and compared with recent baseline methods graph attention network (GAT), GCN-based technique for unsupervised community detection and Markov random fields combined with graph convolutional network (MRFasGCN).Design/methodology/approachThis work presents the method for identifying communities that combines the notion of node classification via message passing with the architecture of a semi-supervised graph neural network. Six benchmark datasets, namely, Cora, CiteSeer, ACM, Karate, IMDB and Facebook, have been used in the experimentation.FindingsIn the first set of experiments, the scaled normalized average matrix of all neighbor's features including the node itself was obtained, followed by obtaining the weighted average matrix of low-dimensional nodes. In the second set of experiments, the average weighted matrix was forwarded to the GCN with two layers and the activation function for predicting the node class was applied. The results demonstrate that node classification with GCN can improve the performance of identifying communities on graph datasets.Originality/valueThe experiment reveals that the CommunityGCN approach has given better results with accuracy, normalized mutual information, F1 and modularity scores of 91.26, 79.9, 92.58 and 70.5 per cent, respectively, for detecting communities in the graph network, which is much greater than the range of 55.7–87.07 per cent reported in previous literature. Thus, it has been concluded that the GCN with node classification models has improved the accuracy.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Deep Learning-based Community Detectionmentioning

confidence: 99%

CommunityGCN: community detection using node classification with graph convolution network

Bhattacharya

Nagwani²,

Tripathi³

2023

DTA

View full text Add to dashboard Cite

show abstract

“…However, Self-training may introduce noise while expanding the dataset. However, Selfsupervised learning may have an advancing effect on solving the problem of unstable performance of GNNs in settings with too few labeled nodes [38][39][40].…”

Section: Graphsage Uses a Multi-layer Aggregation Functionmentioning

confidence: 99%

Review of Image Classification Algorithms Based on Graph Convolutional Networks

Tang

2023

EAI Endorsed Trans AI Robotics

View full text Add to dashboard Cite

In recent years, graph convolutional networks (GCNs) have gained widespread attention and applications in image classification tasks. While traditional convolutional neural networks (CNNs) usually represent images as a two-dimensional grid of pixels when processing image data, the classical model of graph neural networks (GNNs), GCNs, can effectively handle data with graph structure, such as social networks, recommender systems, and molecular structures. In this paper, we will introduce the problems that graph convolutional networks have had, such as over-smoothing, and the methods to solve them, and suggest some possible future directions.

show abstract

Local Spectral for Polarized Communities Search in Attributed Signed Network

Yang

Wang

et al. 2023

Database Systems for Advanced Applications

View full text Add to dashboard Cite

Hierarchical attention network for attributed community detection of joint representation

Cited by 10 publications

References 33 publications

CommunityGCN: community detection using node classification with graph convolution network

CommunityGCN: community detection using node classification with graph convolution network

Review of Image Classification Algorithms Based on Graph Convolutional Networks

Local Spectral for Polarized Communities Search in Attributed Signed Network

Contact Info

Product

Resources

About