Incorporating Interventional Independence Improves Robustness against Interventional Distribution Shift
利用干预独立性提高对干预分布偏移的稳健性
We study the problem of learning robust discriminative representations of causally related latent variables given the underlying causal graph and a training set comprising passively collected observational data and interventional data obtained through targeted interventions on some of these latent variables. We desire to learn representations that are robust against the resulting interventional distribution shifts. Existing approaches treat observational and interventional…