Improving Fair Predictions Using Variational Inference In Causal Models
arXiv:2008.10880
Abstract
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.
References in corpus (13)
- Adam: A Method for Stochastic Optimization
- Stochastic Backpropagation and Approximate Inference in Deep Generative Models
- Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs)
- Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations
- DRAW: A Recurrent Neural Network For Image Generation
- Counterfactual Fairness
- A Recurrent Latent Variable Model for Sequential Data
- Causal Effect Inference with Deep Latent-Variable Models
- On the definition of a confounder
- Causal Reasoning for Algorithmic Fairness
- A causal framework for discovering and removing direct and indirect discrimination
- Wrong side of the tracks: Big Data and Protected Categories
- Optimal Training of Fair Predictive Models