GegenNet predicts link signs in signed bipartite graphs with Gegenbauer-polynomial spectral filters on positive and negative edges, reporting up to 4.28% AUC and 11.69% F1 gains over 11 baselines.
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
-
GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphs
GegenNet predicts link signs in signed bipartite graphs with Gegenbauer-polynomial spectral filters on positive and negative edges, reporting up to 4.28% AUC and 11.69% F1 gains over 11 baselines.