Graph representation learning via enhanced GNNs and transformers
Abstract In recent years, graph transformers (GTs) have captured increasing attention within the graph domain. To address the prevalent deficiencies in local feature learning and edge information utilization inherent to GTs, we propose EHDGT, a novel graph representation learning method based on enh...
Saved in:
| Main Authors: | Hongrui Mu, Chengchen Zhou, Qiancheng Yu, Qunyue Mu |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-08688-7 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
Research on GNNs with stable learning
by: Wenbin Li, et al.
Published: (2025-08-01) -
Dual stream graph augmented transformer model integrating BERT and GNNs for context aware fake news detection
by: Hejamadi Rama Moorthy, et al.
Published: (2025-07-01) -
Transformer based models with hierarchical graph representations for enhanced climate forecasting
by: T. Bhargava Ramu, et al.
Published: (2025-07-01) -
An edge enhancement graph neural network model with node discrimination for knowledge graph representation learning
by: Tao Wang, et al.
Published: (2025-04-01) -
PairReg: A method for enhancing the learning of molecular structure representation in equivariant graph neural networks
by: Zhen Ren, et al.
Published: (2025-01-01)