This article is Part 2 in a 3 part series and focuses on comparing the different methods of unlearning. Part 1 reviews some important machine learning concepts and defines many of the key terms, including unlearning.
Machine unlearning is a new research area that focuses on unlearning a data point, dᵤ, which was used to train a machine learning model, here denoted Mᵒʳⁱᵍⁱᶰᵃˡ. In doing so, we hope to convert Mᵒʳⁱᵍⁱᶰᵃˡ into a model Mᵘᶰˡᵉᵃʳᶰᵉᵈ which is not influenced by dᵤ. The naive approach is to retrain an eager model on all data points except dᵤ, resulting in Mᶰᵃⁱᵛᵉ. …
Before privacy became a mainstream consideration, we rarely considered what companies did with our data. Personally, I didn’t care how companies like Facebook or Google were using my data until the famous Facebook-Cambridge Analytica scandal of 2018 . These and other instances of data misuse emphasized the importance of strong privacy regulation, such as the ‘right to be forgotten’  and the ‘General Data Protection Regulation’. Their intent is evident: we, as users and data contributors, have the right to withhold our data.
I’m a Google AI Resident. My research interests include deep learning and data privacy. My hobbies include rock climbing and cooking. My thoughts are my own.