FairPFN pre-trains a transformer on synthetic structural-causal-model data so it can remove the causal effect of a binary protected attribute from tabular predictions without a user-supplied causal graph.
Fair in-context learning via latent concept variables
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
FairPFN: A Tabular Foundation Model for Causal Fairness
FairPFN pre-trains a transformer on synthetic structural-causal-model data so it can remove the causal effect of a binary protected attribute from tabular predictions without a user-supplied causal graph.