Self-Interpretable Reinforcement Learning via Rule Ensembles

Yue Yang, Fan Yang, Yu Bai, Hao Wang

Abstract: Machine unlearning has become a focal point in recent research, yet the specific area of feature unlearning has not been thoroughly explored. Feature unlearning involves eliminating specific features' effects from an already trained model, presenting distinct challenges that are not yet comprehensively addressed. This paper presents a novel and straightforward approach to feature unlearning that employs a tactical shuffling of the features designated for removal. By redistributing the values of the features targeted for unlearning throughout the original training dataset and subsequently fine-tuning the model with this shuffled data, our proposed method provides a theoretical guarantee for effective feature unlearning. Under mild assumptions, our method can effectively disrupt the established correlations between unlearned features and the label, while preserving the relationships between the remaining features and the label. Across both tabular and image datasets, our empirical results show that our method not only effectively and efficiently removes the influence of designated features but also preserves the information content of the remaining features.