SILO: Domain Counterfactuals for Explainability, Fairness, and Domain Generalization
Abstract: Although incorporating causal concepts into deep learning shows promise for increasing explainability, fairness, and robustness, existing methods require unrealistic assumptions or aim to recover the full latent causal model. This talk proposes an alternative: domain counterfactuals. Domain counterfactuals ask a more concrete question: “What would a sample look like …