Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning

TL;DR

This paper introduces S3T, a scalable exact machine unlearning framework that uses parameter-efficient fine-tuning and data slicing to enable efficient data deletion with minimal retraining and performance impact.

Contribution

The paper proposes S3T, a novel unlearning framework that improves deletion efficiency and model performance using sequential training of disjoint data slices and parameter isolation.

Findings

S3T achieves superior deletion capabilities compared to baselines.

S3T maintains high model performance after multiple deletions.

Theoretical and empirical results validate S3T's effectiveness.

Abstract

Machine unlearning is the process of efficiently removing the influence of a training data instance from a trained machine learning model without retraining it from scratch. A popular subclass of unlearning approaches is exact machine unlearning, which focuses on techniques that explicitly guarantee the removal of the influence of a data instance from a model. Exact unlearning approaches use a machine learning model in which individual components are trained on disjoint subsets of the data. During deletion, exact unlearning approaches only retrain the affected components rather than the entire model. While existing approaches reduce retraining costs, it can still be expensive for an organization to retrain a model component as it requires halting a system in production, which leads to service failure and adversely impacts customers. To address these challenges, we introduce an exact unlearning framework -- Sequence-aware Sharded Sliced Training (S3T), which is designed to enhance the deletion capabilities of an exact unlearning system while minimizing the impact on model's performance. At the core of S3T, we utilize a lightweight parameter-efficient fine-tuning approach that enables parameter isolation by sequentially training layers with disjoint data slices. This enables efficient unlearning by simply deactivating the layers affected by data deletion. Furthermore, to reduce the retraining cost and improve model performance, we train the model on multiple data sequences, which allows S3T to handle an increased number of deletion requests. Both theoretically and empirically, we demonstrate that S3T attains superior deletion capabilities and enhanced performance compared to baselines across a wide range of settings.