One for All: Universal Topological Primitive Transfer for Graph Structure Learning
–Neural Information Processing Systems
The non-Euclidean geometry inherent in graph structures fundamentally impedes cross-graph knowledge transfer.
Neural Information Processing Systems
Jun-15-2026, 16:02:07 GMT
- Genre:
- Research Report
- New Finding (1.00)
- Experimental Study (1.00)
- Research Report
- Industry:
- Information Technology (0.67)
- Health & Medicine (0.46)
- Technology:
- Information Technology
- Information Management (1.00)
- Communications (1.00)
- Data Science > Data Mining (0.93)
- Artificial Intelligence
- Representation & Reasoning (1.00)
- Natural Language (1.00)
- Machine Learning
- Neural Networks (1.00)
- Performance Analysis > Accuracy (0.46)
- Information Technology