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.
The emerging field of signal processing on graphs: Extending high- dimensional data analysis to networks and other irregular domains,
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.