Machine unlearning

The definition

Removing the influence of specific training data from a model's parameters so the model is approximately what retraining without that data would produce. Exact unlearning of a large model means retraining it; approximate methods are judged against a retrained reference. The term is often misused for output suppression, refusal or knowledge editing, which remove nothing from the weights.

The same words the glossary hub and the public data mirror carry; this page is the stable address for the term.

Related terms

• Knowledge

  What a system currently takes to be true: facts with a validity and a source, as distinct from the records they came from. A memory is a record of what was…

• Erasure ladder

  This site's ordering of the twelve operations the word “forget” is used for, from correcting a wrong record to verifying that a deleted one no longer shapes…

Where it shows up on this site

• The erasure ladder · ReferenceTwelve things forget can mean, from a correction to verified non-influence