ApproxBias documentation
Welcome to the ApproxBias’s documentation. This is to help you reproduce our work from
Does machine bring in extra bias in learning? Approximating fairness in models promptly [arXiv 2405.09251]
Approximating discrimination within models when faced with several non-binary sensitive attributes [arXiv 2408.06099]
We proposed a fairness measure named harmonic fairness measure via manifolds (HFM) with three optional versions, which deals with a fine-grained discrimination evaluation for one or more sensitive attributes (sen-att-s). HFM relies on the Euclidean Hausdorff distance, of which the direct computation is rather heavy. To accelerate the distance computation, we further proposed a few approximation algorithms for efficient bias evaluation.
To get started quickly, see an example here
To understand the methodology, see methodology
To reproduce the empirical results, see instructions