GNA predicts GED and produces hard one-to-one node alignments via an unsupervised Gumbel-Sinkhorn module, outperforming prior soft-alignment models on three datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Graph Similarity Computation via Interpretable Neural Node Alignment
GNA predicts GED and produces hard one-to-one node alignments via an unsupervised Gumbel-Sinkhorn module, outperforming prior soft-alignment models on three datasets.