When Unlearning Is Free: Leveraging Low Influence Points to Reduce Computational Costs

Apple Machine Learning Research · 2 months ago · 31

The authors propose an unlearning method that uses influence functions to find training points with negligible impact and then unlearns only the relevant subset. Up to about 50 percent computational savings are reported on real-world empirical examples by shrinking the dataset before unlearning. The approach changes unlearning by avoiding processing every point in the forget set equally, reducing compute cost.