IMPA-HGAE masks and reconstructs features and meta-paths in heterogeneous graphs and propagates intermediate meta-path node information, yielding competitive but not uniformly best node-classification results across four datasets.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
IMPA-HGAE:Intra-Meta-Path Augmented Heterogeneous Graph Autoencoder
IMPA-HGAE masks and reconstructs features and meta-paths in heterogeneous graphs and propagates intermediate meta-path node information, yielding competitive but not uniformly best node-classification results across four datasets.