Learning Unbiased Representations via Mutual Information Backpropagation
Learning Unbiased Representations via Mutual Information Backpropagation
We are interested in learning data-driven representations that can generalize well, even when trained on inherently biased data. In particular, we face the case where some attributes (bias) of the data, if learned by the model, can severely compromise its generalization properties. We tackle this problem through the lens of …