×
Nov 5, 2021 · In this work we present a novel approach to increase a Neural Network model's fairness during training. We introduce a family of fairness ...
In the current work we investigate the behavior and effect of these regularization components on bias. We deploy them in the context of a recidivism prediction.
We introduce a family of fairness enhancing regularization components that we use in conjunction with the traditional binary-cross-entropy based accuracy loss.
Increasing Fairness in Predictions Using Bias Parity Score Based Loss Function Regularization ...
This work proposes a novel approach to increase a Neural Network model's fairness during the training phase.
In this work we present a novel approach to increase a NeuralNetwork model's fairness during training. We introduce a family of fairnessenhancing regularization ...
Nov 5, 2021 · In this work we proposed Bias Parity Score-based fairness metrics and an approach to translate them into correspond- ing loss functions to be ...
People also ask
Increasing Fairness in Predictions Using Bias Parity Score Based Loss Function Regularization ; Jain, Bhanu (Author) ; Elmasri, Ramez 1950- (Author) ; Huber, ...
Fairness for Deep Learning Predictions Using Bias Parity Score Based Loss Function Regularization. Authors. Jain, Bhanu; Huber, Manfred; Elmasri, Ramez.
Missing: Increasing | Show results with:Increasing
We introduce a family of fairness enhancing regularization components that we use in conjunction with the traditional binary-cross-entropy based accuracy loss.