GraphMoRE learns per-node mixtures of Riemannian expert embedding spaces, reducing distortion on graphs that mix tree-like, cycle-like, and flat substructures.
M.; Bruna, J.; LeCun, Y.; Szlam, A.; and Vandergheynst, P
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
-
GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts
GraphMoRE learns per-node mixtures of Riemannian expert embedding spaces, reducing distortion on graphs that mix tree-like, cycle-like, and flat substructures.