What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding.
Hongkang LiMeng WangTengfei MaSijia LiuZaixi ZhangPin-Yu ChenPublished in: CoRR (2024)
Keyphrases
- random walk
- graph representation
- graph structure
- weighted graph
- directed graph
- directed acyclic graph
- graph model
- graph clustering
- graph theoretic
- bipartite graph
- visual attention
- fractal image compression
- stable set
- graph theory
- graph mining
- neural network
- variable length
- spanning tree
- graph matching
- graph structures
- dependency graph
- graph properties