Graph clustering network with structure embedding enhanced
S Ding, B Wu, X Xu, L Guo, L Ding - Pattern Recognition, 2023 - Elsevier
Recently, deep clustering utilizing Graph Neural Networks has shown good performance in
the graph clustering. However, the structure information of graph was underused in existing …
the graph clustering. However, the structure information of graph was underused in existing …
Parameter-agnostic deep graph clustering
Deep graph clustering, efficiently dividing nodes into multiple disjoint clusters in an
unsupervised manner, has become a crucial tool for analyzing ubiquitous graph data …
unsupervised manner, has become a crucial tool for analyzing ubiquitous graph data …
CLP-GCN: Confidence and label propagation applied to Graph Convolutional Networks
M Ghayekhloo, A Nickabadi - Applied Soft Computing, 2023 - Elsevier
Node classification is an important task in many graph-related applications. Recently, graph
neural networks like Graph Convolutional Networks (GCNs) have provided low-dimensional …
neural networks like Graph Convolutional Networks (GCNs) have provided low-dimensional …
Individuality-enhanced and multi-granularity consistency-preserving graph neural network for semi-supervised node classification
X Liu, W Yu - Applied Intelligence, 2023 - Springer
Semi-supervised node classification is an important task that aims at classifying nodes
based on the graph structure, node features, and class labels for a subset of nodes. While …
based on the graph structure, node features, and class labels for a subset of nodes. While …
Confidence correction for trained graph convolutional networks
J Yuan, H Guo, C Zhou, J Ding, Z Kuang, Z Yu, Y Liu - Pattern Recognition, 2024 - Elsevier
Abstract Adopting Graph Convolutional Networks (GCNs) for transductive node classification
is a hot research direction in artificial intelligence. Vanilla GCNs are primarily under …
is a hot research direction in artificial intelligence. Vanilla GCNs are primarily under …
Deep contrastive representation learning for multi-modal clustering
Y Lu, Q Li, X Zhang, Q Gao - Neurocomputing, 2024 - Elsevier
Benefiting from the informative expression capability of contrastive representation learning
(CRL), recent multi-modal learning studies have achieved promising clustering …
(CRL), recent multi-modal learning studies have achieved promising clustering …
[HTML][HTML] MREGDN: Multi-Relation Enhanced Graph Disentangled Network for semi-supervised node classification
X Liu, W Yu - Expert Systems with Applications, 2024 - Elsevier
Many deep graph neural networks perform well in tackling semi-supervised node
classification tasks. However, they often focus on learning a holistic representation for …
classification tasks. However, they often focus on learning a holistic representation for …
Structure-Aware Consensus Network on Graphs with Few Labeled Nodes
Graph node classification with few labeled nodes presents significant challenges due to
limited supervision. Conventional methods often exploit the graph in a transductive learning …
limited supervision. Conventional methods often exploit the graph in a transductive learning …
Semi-supervised heterogeneous graph contrastive learning with label-guided
C Li, G Sun, X Li, J Shan - Applied Intelligence, 2024 - Springer
Abstract Heterogeneous Graph Neural Networks represent a powerful approach to
understand and utilize the intricate structures and semantics within complex graphs. When it …
understand and utilize the intricate structures and semantics within complex graphs. When it …
Synergistic Deep Graph Clustering Network
B Wu, S Ding, X Xu, L Guo, L Ding, X Wu - arXiv preprint arXiv:2406.15797, 2024 - arxiv.org
Employing graph neural networks (GNNs) to learn cohesive and discriminative node
representations for clustering has shown promising results in deep graph clustering …
representations for clustering has shown promising results in deep graph clustering …