SGNN-LS approximates dense multi-hop spectral filters with sparse random-walk graphs, enabling end-to-end training on 111M-node graphs, but the theory for negative filter coefficients has a gap.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Large-Scale Spectral Graph Neural Networks via Laplacian Sparsification: Technical Report
SGNN-LS approximates dense multi-hop spectral filters with sparse random-walk graphs, enabling end-to-end training on 111M-node graphs, but the theory for negative filter coefficients has a gap.