GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Kamhoua, Barakeel Fanseu; Zhang, Lin; Ma, Kaili; Cheng, James; Li, Bo; Han, Bo

doi:10.1145/3544977

Cited by 7 publications

(2 citation statements)

References 80 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Graph convolution [38] embeds node features and topological information into a lowdimensional space by convolutional encoding of the adjacency matrix A and the feature matrix X:…”

Section: Graph Convolutionmentioning

confidence: 99%

Hypergraph network embedding for community detection

Xiang,

You,

Wang

et al. 2024

J Supercomput

View full text Add to dashboard Cite

Using attribute graphs for node embedding to detect community structure has become a popular research topic. However, most of the existing algorithms mainly focus on the network structure and node features, which ignore the higher-order relationships between nodes. In addition, only adopting the original graph structure will suffer from sparsity problems, and will also result in sub-optimal node clustering performance. In this paper, we propose a hypergraph network embedding (HGNE) for community detection to solve the above problems. Firstly, we construct potential connections based on the shared feature information of the nodes. By fusing the original topology with feature-based potential connections, both the explicit and implicit relationships are encoded into the node representations, thus alleviating the sparsity problem. Secondly, for integrating the higher-order relationship, we adopt hypergraph convolution to encode the higherorder correlations. To constrain the quality of the node embedding, the spectral hypergraph embedding loss is utilized. Furthermore, we design a dual-contrast mechanism, which draws similar nodes closer by comparing the representations of different views. This mechanism can efficiently prevent multi-node classes from distorting less-node classes. Finally, the dual-contrast mechanism is jointly optimized with self-training clustering to obtain more robust node representations, thus improving the clustering results. Extensive experiments on five datasets indicate the superiority and effectiveness of HGNE.

show abstract

“…Graph convolution [38] embeds node features and topological information into a lowdimensional space by convolutional encoding of the adjacency matrix A and the feature matrix X:…”

Section: Graph Convolutionmentioning

confidence: 99%

Hypergraph network embedding for community detection

Xiang,

You,

Wang

et al. 2024

J Supercomput

View full text Add to dashboard Cite

show abstract

“…As more and more complicated data from the real world are represented in graphs with attributed nodes, attributed grap h clustering (AGC) has become a significant issue in graph mining. Kamhoua et al [45] suggested an expanded general graph convolution framework for attributed graph clustering (GRACE), often known as an AGC tasks. Zhang et al [21] suggested a community affiliation graph model that can capture overlapping, non-overlapping, and hierarchical layered overlapping communities successfully.…”

Section: Related Workmentioning

confidence: 99%

A Locally and Globally Tuned Metaheuristic Optimization for Overlapping Community Detection

Mallick¹,

Giri²,

Mishra³

2023

MJCS

View full text Add to dashboard Cite

Many people use online social networks to share their opinions and information in this digital age. The number of people engaged and their dynamic nature pose a major challenge for social network analysis (SNA). Community detection is one of the most critical and fascinating issues in social network analysis. Researchers frequently employ node features and topological structures to recognize important and meaningful performance in order to locate non-overlapping communities. We introduce a locally and globally tuned multi-objective biogeography-based optimization (LGMBBO) technique in this research for detecting overlapping communities based on the number of connections and node similarity. Four real- world online social network datasets were used in the experiment to assess the quality of both overlapping and non-overlapping partitions. As a result, the model generates a set of solutions that have the best topological structure of a network with node properties. The suggested model will increase their productivity and enhance their abilities to identify significant and pertinent communities.

show abstract

Identifying vital nodes for influence maximization in attributed networks

Wang

Zheng

Liu

2022

Sci Rep

View full text Add to dashboard Cite

Identifying a set of vital nodes to achieve influence maximization is a topic of general interest in network science. Many algorithms have been proposed to solve the influence maximization problem in complex networks. Most of them just use topology information of networks to measure the node influence. However, the node attribute is also an important factor for measuring node influence in attributed networks. To tackle this problem, we first propose an extension model of linear threshold (LT) propagation model to simulate the information propagation in attributed networks. Then, we propose a novel community-based method to identify a set of vital nodes for influence maximization in attributed networks. The proposed method considers both topology influence and attribute influence of nodes, which is more suitable for identifying vital nodes in attributed networks. A series of experiments are carried out on five real world networks and a large scale synthetic network. Compared with CELF, IMM, CoFIM, HGD, NCVoteRank and K-Shell methods, experimental results based on different propagation models show that the proposed method improves the influence spread by $$-2.28\% \, \textrm{to} \, 4.76\%$$ - 2.28 % to 4.76 % , $$-2.50\% \, \textrm{to} \, 16.97\%$$ - 2.50 % to 16.97 % , $$0.18\% \, \textrm{to} \, 16.07\%$$ 0.18 % to 16.07 % , $$0.22\% \, \textrm{to} \, 41.82\%$$ 0.22 % to 41.82 % , $$0.23\% \, \textrm{to} \, 11.24\%$$ 0.23 % to 11.24 % and $$10.78\% \, \textrm{to} \, 75.22\%$$ 10.78 % to 75.22 % .

show abstract

GRACE: A General Graph Convolution Framework for Attributed Graph Clustering

Cited by 7 publications

References 80 publications

Hypergraph network embedding for community detection

Hypergraph network embedding for community detection

A Locally and Globally Tuned Metaheuristic Optimization for Overlapping Community Detection

Identifying vital nodes for influence maximization in attributed networks

Contact Info

Product

Resources

About