no code implementations • 4 Feb 2022 • Mohit Wadhwa, Mohan Bhambhani, Ashvini Jindal, Uma Sawant, Ramanujam Madhavan
Counterfactual fairness methods address the question: How would the prediction change if the sensitive identity attributes referenced in the text instance were different?
no code implementations • 21 Oct 2020 • Ramanujam Madhavan, Mohit Wadhwa
Although cross product between a pair of vectors is defined in three dimensional, the approach is extended to learn N dimensional embeddings while maintaining the non-commutative property.
no code implementations • 26 Feb 2020 • Ramanujam Madhavan, Mohit Wadhwa
These models are trained over historical data that may contain information about sensitive attributes such as race, sex, religion, etc.