CausalMP rewires a graph using conditional-entropy asymmetry and mutual information, then trains a GNN on the rewired graph to improve link prediction and few-shot node classification.
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
-
Heterophilic Graph Neural Networks Optimization with Causal Message-passing
CausalMP rewires a graph using conditional-entropy asymmetry and mutual information, then trains a GNN on the rewired graph to improve link prediction and few-shot node classification.