Skip to main content
Search

Seth R Flaxman

1 related articles

Subscribe to updates
  1. arXiv

    FADO swaps correlation for intervention in tabular explanations, returning every feature's intervention effect in one forward pass

    Explanation for tabular machine learning has largely meant predictive attribution, which asks whether a feature helps predict the outcome and captures correlation rather than causation. FADO instead trains a prior-fitted network on synthetic tables drawn from structural causal models, where the true intervention effects are known and serve as supervision, so at test time a single observational table yields the full vector of per-feature intervention effects in one forward pass. In settings where standard predictive attribution fails, including proxy variables, confounders, colliders and placebos, FADO produces a feature-importance ranking that differs from predictive attribution and drives non-causal but predictive features toward zero.

You’re all caught up