LLPE applies learnable Chebyshev weights to the full Laplacian spectrum so graph positional encodings capture heterophilous as well as homophilous structure, improving node classification accuracy.
Yes (b) An analysis of the properties and complexity (time, space, sample size) of any algorithm
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
-
Learning Laplacian Positional Encodings for Heterophilous Graphs
LLPE applies learnable Chebyshev weights to the full Laplacian spectrum so graph positional encodings capture heterophilous as well as homophilous structure, improving node classification accuracy.