The Causal Loss: Driving Correlation to Imply Causation
This addresses the limitation of standard ML models in handling causal inconsistencies, potentially improving robustness in applications where causality matters, though it appears incremental as a regularizer added to existing methods.
The paper tackles the problem of correlation-based machine learning failing when causality is inconsistent, by proposing a model-agnostic Causal Loss that improves interventional prediction quality, with experimental results showing it endows non-causal models with interventional capabilities.
Most algorithms in classical and contemporary machine learning focus on correlation-based dependence between features to drive performance. Although success has been observed in many relevant problems, these algorithms fail when the underlying causality is inconsistent with the assumed relations. We propose a novel model-agnostic loss function called Causal Loss that improves the interventional quality of the prediction using an intervened neural-causal regularizer. In support of our theoretical results, our experimental illustration shows how causal loss bestows a non-causal associative model (like a standard neural net or decision tree) with interventional capabilities.