Markov Chain Monte Carlo-Based Machine Unlearning: Unlearning What Needs to be Forgotten

TL;DR

This paper introduces a Markov chain Monte Carlo-based algorithm for machine unlearning, enabling efficient removal of specific training data effects from models, which is crucial for privacy and security, without retraining from scratch.

Contribution

The paper proposes a novel MCMC-based unlearning algorithm that effectively and efficiently removes data influence from trained models and explains data impact on predictions.

Findings

MCU effectively unlearns data subsets from models.

MCU outperforms existing algorithms in efficiency and effectiveness.

MCU helps identify adversarial data and supports data privacy rights.

Abstract

As the use of machine learning (ML) models is becoming increasingly popular in many real-world applications, there are practical challenges that need to be addressed for model maintenance. One such challenge is to 'undo' the effect of a specific subset of dataset used for training a model. This specific subset may contain malicious or adversarial data injected by an attacker, which affects the model performance. Another reason may be the need for a service provider to remove data pertaining to a specific user to respect the user's privacy. In both cases, the problem is to 'unlearn' a specific subset of the training data from a trained model without incurring the costly procedure of retraining the whole model from scratch. Towards this goal, this paper presents a Markov chain Monte Carlo-based machine unlearning (MCU) algorithm. MCU helps to effectively and efficiently unlearn a trained model from subsets of training dataset. Furthermore, we show that with MCU, we are able to explain the effect of a subset of a training dataset on the model prediction. Thus, MCU is useful for examining subsets of data to identify the adversarial data to be removed. Similarly, MCU can be used to erase the lineage of a user's personal data from trained ML models, thus upholding a user's "right to be forgotten". We empirically evaluate the performance of our proposed MCU algorithm on real-world phishing and diabetes datasets. Results show that MCU can achieve a desirable performance by efficiently removing the effect of a subset of training dataset and outperform an existing algorithm that utilizes the remaining dataset.