Introduces coarse and fine feature-graph alignment notions to enable subgraph sampling that preserves Laplacian trace and spectral properties for improved GNN transferability without relying on complete graph structure.
How to learn a graph from smooth signals,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.SP 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Sampling Transferable Graph Neural Networks with Limited Graph Information
Introduces coarse and fine feature-graph alignment notions to enable subgraph sampling that preserves Laplacian trace and spectral properties for improved GNN transferability without relying on complete graph structure.