PFD-BDCM is a diffusion-based structural causal model that represents dynamic spatio-temporal confounders via conditional autoregressive processes and functional data via basis expansions, with theoretical preservation of causal effects and empirical outperformance on synthetic and air-pollution dat
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
stat.ML 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Partially Functional Dynamic Backdoor Diffusion-based Causal Model
PFD-BDCM is a diffusion-based structural causal model that represents dynamic spatio-temporal confounders via conditional autoregressive processes and functional data via basis expansions, with theoretical preservation of causal effects and empirical outperformance on synthetic and air-pollution dat