Notes on Mixed-Privacy Forgetting in Deep Networks
Disclaimer: This is part of my notes on AI research papers. I do this to learn and communicate what I understand. Feel free to comment if you have any suggestion, that would be very much appreciated. The following post is a comment on the paper Mixed-Privacy Forgetting in Deep Networks by Aditya Golatkar, Alessandro Achille, Avinash Ravichandran, Marzia Polito, and Stefano Soatto. Golatkar et. al. introduce a novel method for forgetting in a mixed-privacy setting, where a core subset of the training samples will not be forgotten....