Improving Fair Predictions Using Variational Inference In Causal Models
This work addresses fairness in machine learning predictions, particularly for sensitive applications like social welfare, though it appears incremental by building on existing causal fairness metrics and variational inference techniques.
The authors tackled the problem of algorithmic fairness by proposing FairTrade, a method that integrates fairness constraints on sensitive causal paths using variational inference to account for unobserved confounders, resulting in flexible prediction models validated on simulated and real-world data for detecting unlawful social welfare.
The importance of algorithmic fairness grows with the increasing impact machine learning has on people's lives. Recent work on fairness metrics shows the need for causal reasoning in fairness constraints. In this work, a practical method named FairTrade is proposed for creating flexible prediction models which integrate fairness constraints on sensitive causal paths. The method uses recent advances in variational inference in order to account for unobserved confounders. Further, a method outline is proposed which uses the causal mechanism estimates to audit black box models. Experiments are conducted on simulated data and on a real dataset in the context of detecting unlawful social welfare. This research aims to contribute to machine learning techniques which honour our ethical and legal boundaries.