Unlearning Protected User Attributes in Recommendations with Adversarial Training. (arXiv:2206.04500v1 [cs.IR])

Collaborative filtering algorithms capture underlying consumption patterns,
including the ones specific to particular demographics or protected information
of users, e.g. gender, race, and location. These encoded biases can influence
the decision of a recommendation system (RS) towards further separation of the
contents provided to various demographic subgroups, and raise privacy concerns
regarding the disclosure of users' protected attributes. In this work, we
investigate the possibility and challenges of removing specific protected
information of users from the learned interaction representations of …

adversarial attributes ir training