Supra-Laplacian positional encodings generally improve temporal GNN link prediction, and approximate iterative computation (LOBPCG) can replace exact eigendecomposition with little performance loss.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Understanding and Improving Laplacian Positional Encodings For Temporal GNNs
Supra-Laplacian positional encodings generally improve temporal GNN link prediction, and approximate iterative computation (LOBPCG) can replace exact eigendecomposition with little performance loss.