MHCL learns per-metapath hyperbolic spaces with learnable curvature and a hyperbolic contrastive loss to separate metapath embeddings, reporting modest gains over existing heterogeneous graph embedding baselines.
Poincar ´e embeddings for learning hierarchical representations,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Metapath-based Hyperbolic Contrastive Learning for Heterogeneous Graph Embedding
MHCL learns per-metapath hyperbolic spaces with learnable curvature and a hyperbolic contrastive loss to separate metapath embeddings, reporting modest gains over existing heterogeneous graph embedding baselines.