Search Results for author:
Found 3 papers, 0 papers with code
Difficulty-Based Sampling for Debiased Contrastive Representation Learning
We theoretically show that the triplet loss amplifies the bias in self-supervised representation learning.
Group-Aware Threshold Adaptation for Fair Classification
As we only need an estimated probability distribution of model output instead of the classification model structure, our post-processing model can be applied to a wide range of classification models and improve fairness in a model-agnostic manner and ensure privacy.
Adversarial Fairness Network
To achieve this goal, we reformulate the data input by eliminating the sensitive information and strengthen model fairness by minimizing the marginal contribution of the sensitive feature.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
