Learning Joint Interventional Effects from Single-Variable Interventions in Additive Models
This addresses a challenge in causal inference for domains where joint intervention data is hard to obtain, offering a practical solution with incremental improvements over observational methods.
The paper tackles the problem of estimating causal effects of joint interventions when only observational data and single-variable interventions are available, showing that joint effects can be inferred for nonlinear additive models without joint interventional data, with experiments demonstrating performance comparable to models trained on joint data.
Estimating causal effects of joint interventions on multiple variables is crucial in many domains, but obtaining data from such simultaneous interventions can be challenging. Our study explores how to learn joint interventional effects using only observational data and single-variable interventions. We present an identifiability result for this problem, showing that for a class of nonlinear additive outcome mechanisms, joint effects can be inferred without access to joint interventional data. We propose a practical estimator that decomposes the causal effect into confounded and unconfounded contributions for each intervention variable. Experiments on synthetic data demonstrate that our method achieves performance comparable to models trained directly on joint interventional data, outperforming a purely observational estimator.