Timezone: »

 
Poster
DECAF: Generating Fair Synthetic Data Using Causally-Aware Generative Networks
Boris van Breugel · Trent Kyono · Jeroen Berrevoets · Mihaela van der Schaar

Thu Dec 09 08:30 AM -- 10:00 AM (PST) @
in Poster Session 6 »

Machine learning models have been criticized for reflecting unfair biases in the training data. Instead of solving for this by introducing fair learning algorithms directly, we focus on generating fair synthetic data, such that any downstream learner is fair. Generating fair synthetic data from unfair data - while remaining truthful to the underlying data-generating process (DGP) - is non-trivial. In this paper, we introduce DECAF: a GAN-based fair synthetic data generator for tabular data. With DECAF we embed the DGP explicitly as a structural causal model in the input layers of the generator, allowing each variable to be reconstructed conditioned on its causal parents. This procedure enables inference time debiasing, where biased edges can be strategically removed for satisfying user-defined fairness requirements. The DECAF framework is versatile and compatible with several popular definitions of fairness. In our experiments, we show that DECAF successfully removes undesired bias and - in contrast to existing methods - is capable of generating high-quality synthetic data. Furthermore, we provide theoretical guarantees on the generator's convergence and the fairness of downstream models.

Keywords: Machine Learning · Generative Model · Causality · Fairness

Author Information

Boris van Breugel (University of Cambridge)
Trent Kyono (UCLA)
Jeroen Berrevoets (University of Cambridge)
Mihaela van der Schaar (University of Cambridge)

More from the Same Authors