Publikation
(chi)SPN: Characteristic Interventional Sum-Product Networks for Causal Inference in Hybrid Domains
Harsh Poonia; Moritz Willig; Zhongjie Yu; Matej Zecevic; Kristian Kersting; Devendra Singh Dhami
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2408.07545, Pages 1-17, arXiv, 2024.
Zusammenfassung
Causal inference in hybrid domains, characterized
by a mixture of discrete and continuous variables,
presents a formidable challenge. We take a step
towards this direction and propose Characteristic
Interventional Sum-Product Network (χSPN) that
is capable of estimating interventional distributions
in presence of random variables drawn from mixed
distributions. χSPN uses characteristic functions in
the leaves of an interventional SPN (iSPN) thereby
providing a unified view for discrete and continu-
ous random variables through the Fourier–Stieltjes
transform of the probability measures. A neural
network is used to estimate the parameters of the
learned iSPN using the intervened data. Our ex-
periments on 3 synthetic heterogeneous datasets
suggest that χSPN can effectively capture the inter-
ventional distributions for both discrete and contin-
uous variables while being expressive and causally
adequate. We also show that χSPN generalize to
multiple interventions while being trained only on
single intervention data.