Debiasing Machine Unlearning with Counterfactual Examples
This addresses bias issues in machine unlearning for applications requiring data deletion under privacy regulations like the right to be forgotten, representing an incremental improvement.
The paper tackles bias in machine unlearning processes, which degrade model accuracy due to uneven data removal and algorithmic contamination, by introducing an intervention-based approach using counterfactual examples to debias the forgetting procedure, resulting in outperformance over existing baselines on evaluation metrics.
The right to be forgotten (RTBF) seeks to safeguard individuals from the enduring effects of their historical actions by implementing machine-learning techniques. These techniques facilitate the deletion of previously acquired knowledge without requiring extensive model retraining. However, they often overlook a critical issue: unlearning processes bias. This bias emerges from two main sources: (1) data-level bias, characterized by uneven data removal, and (2) algorithm-level bias, which leads to the contamination of the remaining dataset, thereby degrading model accuracy. In this work, we analyze the causal factors behind the unlearning process and mitigate biases at both data and algorithmic levels. Typically, we introduce an intervention-based approach, where knowledge to forget is erased with a debiased dataset. Besides, we guide the forgetting procedure by leveraging counterfactual examples, as they maintain semantic data consistency without hurting performance on the remaining dataset. Experimental results demonstrate that our method outperforms existing machine unlearning baselines on evaluation metrics.