Research map / Graph learning / Graph self-supervised learning
One for All: Universal Topological Primitive Transfer for Graph Structure Learning
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 topological primitives as transferable semantic units for cross-graph structural knowledge transfer in graph structure learning (NeurIPS 2025).
Problem
Non-Euclidean graph geometry impedes cross-graph knowledge transfer for graph structure learning; lacks specialized benchmarks, aligned semantic representations, and systematic transfer methods.
Approach
Treats topological primitives as transferable semantic units of graph structural knowledge, inspired by texture transfer in computer vision, to enable universal cross-graph transfer.
Closest papers by meaning
- Contextual Structure Knowledge Transfer for Graph Neural Networks (AAAI 2025 · similarity 0.91)
- The Underappreciated Power of Vision Models for Graph Structural Understanding (NeurIPS 2025 · similarity 0.89)
- Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures (NeurIPS 2024 · similarity 0.89)
- Topological Blindspots: Understanding and Extending Topological Deep Learning Through the Lens of Expressivity (ICLR 2025 · similarity 0.88)
- Translating Subgraphs to Nodes Makes Simple GNNs Strong and Efficient for Subgraph Representation Learning (ICML 2024 · similarity 0.88)
- SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs (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.