How to unlearn a learned Machine Learning model ?
This addresses the need for regulation in ML by enabling selective data removal, which is an incremental improvement in model control methods.
The paper tackles the problem of controlling machine learning models by unlearning undesired data, presenting an algorithm with mathematical theory and metrics to evaluate performance on desired data and ignorance of unwanted data.
In contemporary times, machine learning (ML) has sparked a remarkable revolution across numerous domains, surpassing even the loftiest of human expectations. However, despite the astounding progress made by ML, the need to regulate its outputs and capabilities has become imperative. A viable approach to address this concern is by exerting control over the data used for its training, more precisely, by unlearning the model from undesired data. In this article, I will present an elegant algorithm for unlearning a machine learning model and visualize its abilities. Additionally, I will elucidate the underlying mathematical theory and establish specific metrics to evaluate both the unlearned model's performance on desired data and its level of ignorance regarding unwanted data.