Research map / Graph learning / GNN architectures
HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes HubGT, a fast graph transformer that uses decoupled hierarchy labeling (hub-based) to replace quadratic global attention for scalable learning on large graphs.
Problem
Graph Transformers use global attention with quadratic complexity in graph size, limiting their application to large graphs, and current scalable GT designs struggle to represent graph information efficiently.
Approach
Uses decoupled hierarchy labeling to encode graph structure for a fast graph transformer, aiming to keep effective graph representation while improving learning efficiency over global attention.
Closest papers by meaning
- NLGT: Neighborhood-based and Label-enhanced Graph Transformer Framework for Node Classification (AAAI 2025 · similarity 0.90)
- Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework (NeurIPS 2025 · similarity 0.89)
- Generalizable Insights for Graph Transformers in Theory and Practice (NeurIPS 2025 · similarity 0.89)
- Less is More: on the Over-Globalizing Problem in Graph Transformers (ICML 2024 · similarity 0.88)
- What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding (ICML 2024 · similarity 0.88)
- Generative Graph Pattern Machine (NeurIPS 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.