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 [1]. These and other instances of data misuse emphasized the importance of strong privacy regulation, such as the ‘right to be forgotten’ [2] and the ‘General Data Protection Regulation’. Their intent is evident: we, as users and data contributors, have the right to withhold our data.

These regulations were a huge step forward because they gave us the right and power to protect…

Christopher Choquette

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.

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store