Group-robust Machine Unlearning

Understand

Machine unlearning is an emerging paradigm to remove the influence of specific training data (i.e., the forget set) from a model while preserving its knowledge of the rest of the data (i.e., the retain set).

• Previous approaches assume the forget data to be uniformly distributed from all training datapoints.
• However, if the data to unlearn is dominant in one group (e.g., ethnicity, gender), we empirically show that performance for this group degrades, leading to fairness issues.
• To perform unlearning while preserving fairness, this work addresses the overlooked problem of non-uniformly distributed forget sets, which we refer to as group-robust machine unlearning.