Research map / Graph learning / Graph self-supervised learning
Training Graph Transformers via Curriculum-Enhanced Attention Distillation
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 a curriculum-enhanced attention distillation method for training Graph Transformers on semi-supervised node classification under label scarcity.
Problem
Training Graph Transformers for node classification is challenging, especially in semi-supervised settings with severely scarce labeled data.
Approach
Uses a curriculum-enhanced attention distillation scheme to transfer knowledge into Graph Transformers to ease training under label scarcity (details truncated in the available abstract).
Closest papers by meaning
- What Improves the Generalization of Graph Transformers? A Theoretical Dive into the Self-attention and Positional Encoding (ICML 2024 · similarity 0.91)
- Towards Principled Graph Transformers (NeurIPS 2024 · similarity 0.89)
- Noisy Node Classification by Bi-level Optimization Based Multi-Teacher Distillation (AAAI 2025 · similarity 0.88)
- Less is More: on the Over-Globalizing Problem in Graph Transformers (ICML 2024 · similarity 0.88)
- Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework (NeurIPS 2025 · similarity 0.88)
- Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification (NeurIPS 2024 · 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.