HA-HeteroGNN uses two-tier attention to produce relevance scores for pruning nodes in heterogeneous graphs, cutting edges by 27% while raising classification accuracy by 2.4-6.1% on a 50,000-record synthetic dataset.
Veli c kovi \'c , G
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Hierarchical Attention-based Graph Neural Network with Relevance-driven Pruning
HA-HeteroGNN uses two-tier attention to produce relevance scores for pruning nodes in heterogeneous graphs, cutting edges by 27% while raising classification accuracy by 2.4-6.1% on a 50,000-record synthetic dataset.