CoGraphNet for enhanced text classification using word-sentence heterogeneous graph representations and improved interpretability
Abstract Text Graph Representation Learning through Graph Neural Networks (TG-GNN) is a powerful approach in natural language processing and information retrieval. However, it faces challenges in computational complexity and interpretability. In this work, we propose CoGraphNet, a novel graph-based...
Saved in:
Main Authors: | Pengyi Li, Xueying Fu, Juntao Chen, Junyi Hu |
---|---|
Format: | Article |
Language: | English |
Published: |
Nature Portfolio
2025-01-01
|
Series: | Scientific Reports |
Subjects: | |
Online Access: | https://doi.org/10.1038/s41598-024-83535-9 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
HGNN-GAMS: Heterogeneous Graph Neural Networks for Graph Attribute Mining and Semantic Fusion
by: Yufei Zhao, et al.
Published: (2024-01-01) -
On the Graph Isomorphism Completeness of Directed and Multidirected Graphs
by: Sebastian Pardo-Guerra, et al.
Published: (2025-01-01) -
An introduction of F-graphs, a graph-theoretic representation of natural numbers
by: E. J. Farrell
Published: (1992-01-01) -
4-REGULAR GRAPH OF DIAMETER 2
by: Đỗ Như An, et al.
Published: (2013-06-01) -
Longest cycles in certain bipartite graphs
by: Pak-Ken Wong
Published: (1998-01-01)