Replacing the weight matrix in SGCN with a KAN layer yields competitive but generally not superior performance on signed community detection and link sign prediction, with high variance across datasets.
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
-
KAN KAN Buff Signed Graph Neural Networks?
Replacing the weight matrix in SGCN with a KAN layer yields competitive but generally not superior performance on signed community detection and link sign prediction, with high variance across datasets.