.png){kind=icon}
.png){kind=icon}
Return
Multi-Head TextGCN: leveraging multi-head attention for enhanced document classification
.png){kind=icon}
PRE
AI
D
M
B
DOI：10.1007/s10586-026-06063-3.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
In this work, we propose Multi-Head TextGCN, a novel extension of the traditional TextGCN that integrates multi-head attention mechanisms into the graph convolutional process. By modeling document and word nodes jointly within a graph and implementing multiple specialized attention heads to capture local, global, and topical semantic interactions, our approach learns richer and more robust feature representations for document classification. Extensive evaluations on several benchmark datasets demonstrate that our model achieves significant improvements in classification accuracy, proving especially effective in low-resource and few-shot learning scenarios. These promising results underscore the potential of our heterogeneous multi-head framework for advancing graph-based text representation learning.
Keywords:
Document classification
TextGCN
Multi-head attention
Graph neural networks
Low-resource scenarios
Natural language processing
Semi-supervised learning
Journal
C
IF:
0
Papers:
691
Citations:
1
Organization
Cited Papers