no code implementations • 29 Apr 2024 • Salvador Robles Herrera, Verya Monjezi, Vladik Kreinovich, Ashutosh Trivedi, Saeid Tizpaz-Niari
However, the precision depends on the ML training algorithm, dataset, and protected attributes.
no code implementations • 9 Apr 2023 • Verya Monjezi, Ashutosh Trivedi, Gang Tan, Saeid Tizpaz-Niari
Guided by the quantitative fairness, we present a causal debugging framework to localize inadequately trained layers and neurons responsible for fairness defects.