PublicationsPublications

Machine Unlearning for Class Removal through SISA-based Deep Neural Network Architectures

Ishrak Hamim Mahi, Siam Ferdous, Md Sakib Sadman Badhon, Nabid Hasan Omi, Md Habibun Nabi Hemel, Farig Yousuf Sadeque, Md. Tanzim Reza

arXiv preprint (cs.CV)

A modified SISA framework with a reinforced replay mechanism and a gating network that removes an entire class from a trained CNN, with little loss in accuracy and far less compute than retraining from scratch. A version is being prepared for an international conference.