<ul><li>Machine Unlearning aims to remove undesired information from trained models without requiring full retraining from scratch.</li><li>This paper investigates and analyzes machine unlearning through the lens of mode connectivity, which refers to the phenomenon where independently trained models can be connected by smooth low-loss paths in the parameter space.</li><li>The study explores mode connectivity in unlearning across various conditions, including different unlearning methods, models trained with and without curriculum learning, and models optimized with different techniques.</li><li>The findings reveal patterns of fluctuation in evaluation metrics and highlight the (dis)similarity between unlearning methods.</li></ul>

Understanding Machine Unlearning Through the Lens of Mode Connectivity

Discover more