Quantifying Feature Contributions to Overall Disparity Using Information Theory. (arXiv:2206.08454v1 [cs.LG])

Web: http://arxiv.org/abs/2206.08454

When a machine-learning algorithm makes biased decisions, it can be helpful
to understand the sources of disparity to explain why the bias exists. Towards
this, we examine the problem of quantifying the contribution of each individual
feature to the observed disparity. If we have access to the decision-making
model, one potential approach (inspired from intervention-based approaches in
explainability literature) is to vary each individual feature (while keeping
the others fixed) and use the resulting change in disparity to quantify its …

arxiv feature information lg theory