Heterogeneous Graph Neural Network for Short Text Classification

Zhang, Bingjie; He, Qing; Zhang, Damin

doi:10.3390/app12178711

Cited by 9 publications

(2 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Further more, the lack of context, the sparsity of short text features and the inability of word embedding and external knowledge bases to supplement short text information are also challenges for short text classification. Aiming to improves classification accuracy and reduces computational difficulty, Zhang [21] bulit a text, word and POS tag-based graph convolutional network which does not require pre-training word embedding as initial node features.…”

Section: Heterogeneous Graph Networkmentioning

confidence: 99%

DialGNN: Heterogeneous Graph Neural Networks for Dialogue Classification

Yan

Zhang

Min

et al. 2023

Preprint

View full text Add to dashboard Cite

Dialogue systems have attracted growing research interests due to its widespread applications in various domains. Existing studies on classification tasks in dialogue systems majorly focus on the sentence-level intent recognition of users’ utterances. While in real-world applications, classification of the entire dialogue, also benefits many downstream tasks such as customer satisfaction analysis, service quality assurance, dialogue topic categorization, etc. In this paper, we propose DialGNN, a heterogeneous graph neural network framework tailored for the problem of dialogue classification which takes the entire dialogue as input. Specifically, a heterogeneous graph is constructed with nodes in different levels of semantic granularity. The graph framework allows flexible integration of various pre-trained language representation models, such as BERT and its variants, which endows DialGNN with powerful text representational capabilities. The experimental results on two real-world datasets demonstrate the robustness and the effectiveness of the proposed DialGNN framework. The implementation of DialGNN and related data are shared through https://github.com/anonymous-auth/ DialGNN.

show abstract

Section: Heterogeneous Graph Networkmentioning

confidence: 99%

DialGNN: Heterogeneous Graph Neural Networks for Dialogue Classification

Yan

Zhang

Min

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Additionally, Heterogeneous graphs are used to explore correlations between different types of nodes and edges, providing valuable insights in various fields such as social network analysis [22,23,24], bioinformatics [25,26,27], and recommendation systems [28,29,30]. GNNs have demonstrated effectiveness in tasks such as node classification [31,32,33], link prediction [34,35,36], graph classification [37,38,39], community detection [40,41,42], and anomaly detection [43,44,45]. Some GNN models have been developed to meet different graph learning needs [46].…”

Section: Introductionmentioning

confidence: 99%

Drug repurposing Based on the DTD-GNN Graph Neural Network: Revealing the Relationships among Drugs, Targets and Diseases

Li,

Ma,

Yang

et al. 2024

Preprint

View full text Add to dashboard Cite

Motivation: The rational modelling of the relationship among drugs, targets and diseases is crucial for drug retargeting. While significant progress has been made in studying binary relationships, further research is needed to deepen our understanding of ternary relationships. The application of graph neural networks in drug retargeting is increasing, but further research is needed to determine the appropriate modelling method for ternary relationships and how to capture their complex multi-feature structure. Results: The aim of this study was to construct relationships among drug, targets and diseases. To represent the complex relationships among these entities, we used a heterogeneous graph structure. Additionally, we propose a DTD-GNN model that combines graph convolutional networks and graph attention networks to learn feature representations and association information, facilitating a more thorough exploration of the relationships. The experimental results demonstrate that the DTD-GNN model outperforms other graph neural network models in terms of AUC, Precision, and F1-score. The study has important implications for gaining a comprehensive understanding of the relationships between drugs and diseases, as well as for further research and application in exploring the mechanisms of drug-disease interactions. The study reveals these relationships, providing possibilities for innovative therapeutic strategies in medicine.

show abstract

SIGAN: Self-inhibited Graph Attention Network for Text Classification

Fang,

2024

Intelligent Systems Design and Applications

View full text Add to dashboard Cite

Heterogeneous Graph Neural Network for Short Text Classification

Cited by 9 publications

References 27 publications

DialGNN: Heterogeneous Graph Neural Networks for Dialogue Classification

DialGNN: Heterogeneous Graph Neural Networks for Dialogue Classification

Drug repurposing Based on the DTD-GNN Graph Neural Network: Revealing the Relationships among Drugs, Targets and Diseases

SIGAN: Self-inhibited Graph Attention Network for Text Classification

Contact Info

Product

Resources

About