A GCN variant that injects two classic topology heuristics, common neighbors and degree heterogeneity, into the convolution weights achieves modest AUC gains over plain GCN on nine datasets.
Novel drug- target interactions via link prediction and network embedding
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Triadic Closure-Heterogeneity-Harmony GCN for Link Prediction
A GCN variant that injects two classic topology heuristics, common neighbors and degree heterogeneity, into the convolution weights achieves modest AUC gains over plain GCN on nine datasets.