Showing 2023Show all
2 papers · 1 filter
cs.LG2023
How Far Can Fairness Constraints Help Recover From Biased Data?
Mohit Sharma, Amit Deshpande
A general belief in fair classification is that fairness constraints incur a trade-off with accuracy, which biased data may worsen. Contrary to this belief, Blum & Stangl (2019) sh…
cs.LG2023
On Comparing Fair Classifiers under Data Bias
Mohit Sharma, Amit Deshpande, Rajiv Ratn Shah
In this paper, we consider a theoretical model for injecting data bias, namely, under-representation and label bias (Blum & Stangl, 2019). We empirically study the effect of varyin…