A graph clustering framework that uses semantic prototypes, cross-view assignment prediction, and Fused Gromov-Wasserstein optimal transport to improve cluster separability and beat prior methods on nine benchmarks.
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
-
THESAURUS: Contrastive Graph Clustering by Swapping Fused Gromov-Wasserstein Couplings
A graph clustering framework that uses semantic prototypes, cross-view assignment prediction, and Fused Gromov-Wasserstein optimal transport to improve cluster separability and beat prior methods on nine benchmarks.