An edge enhancement graph neural network model with node discrimination for knowledge graph representation learning
Abstract The vectorized representation of a knowledge graph is essential for effectively utilizing its implicit knowledge. Graph neural networks (GNNs) are particularly adept at learning graph representations due to their ability to handle graph topologies. However, GNN-based approaches face two mai...
Saved in:
| Main Authors: | Tao Wang, Bo Shen |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2025-04-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-025-01860-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
-
RRDGNN: Relational reflective disentangled graph neural network for entity alignment
by: Xinchen Shi, et al.
Published: (2025-05-01) -
Knowledge graph completion based on iteratively learning embeddings and noise-aware rules
by: Jinglin Zhang, et al.
Published: (2025-07-01) -
Edge-centric optimization: a novel strategy for minimizing information loss in graph-to-text generation
by: Yao Zheng, et al.
Published: (2024-12-01) -
Solving Edges Deletion Problem of Complete Graphs
by: Anwar N. Jasim, et al.
Published: (2024-12-01) -
Spatiotemporal fusion knowledge tracking model based on spatiotemporal graph and fourier graph neural network
by: Yinquan Liu, et al.
Published: (2025-07-01)