Mitigating Unwanted Biases with Adversarial Learning — mentioned by ebalit

Fri, 03 Jul 2020 00:34:11 GMT

It's a setup that is somewhat similar to GANs (and even closer to a related method called Fader Networks): - a first network take the input data and return a representation A (like an embedding vector): let's called it the "censor network" - a second network take this embedding A as input and is trained to predict the class that should be censored (for example the gender of a person) : the "discriminator network" - a third network take the same embedding A as input and is trained to predict the real task of interest (for example the probability of credit default) : the "predictor network" The…

Paper and discussion history. A mention is not an endorsement.

Mitigating Unwanted Biases with Adversarial Learning · HackerPapers discussions

Mitigating Unwanted Biases with Adversarial Learning — mentioned by ebalit