GDC disentangles features into adjustment and confounder representations, aggregates them separately over the network, and uses counterfactual confounders to improve individual treatment effect estimation.
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
-
Graph Disentangle Causal Model: Enhancing Causal Inference in Networked Observational Data
GDC disentangles features into adjustment and confounder representations, aggregates them separately over the network, and uses counterfactual confounders to improve individual treatment effect estimation.