<ul><li>A hybrid framework for effective and efficient machine unlearning has been proposed.</li><li>The framework combines exact machine unlearning and approximate machine unlearning techniques.</li><li>It aims to achieve an overall success by implementing unlearning with acceptable computation cost and improving accuracy.</li><li>Experiments on real datasets show that the proposed framework improves unlearning efficiency by 1.5x to 8x while maintaining comparable accuracy.</li></ul>

A hybrid framework for effective and efficient machine unlearning

Discover more