Learn to Unlearn: Insights Into Machine Unlearning

2024/03/01 by Youyang Qu, Xin Yuan, Ming Ding +4 · 27 citations
Computer Science · Psychology · #Artificial intelligence #Cognitive science #Computer science #Data science #Human–computer interaction #Online Learning and Analytics #Psychology

paper · doi:10.1109/mc.2023.3333319

published in Computer 57(3), 79-90 (IEEE Computer Society)

openalex publication_date 2024/03/01 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/25

Abstract

This article presents a comprehensive review of recent machine unlearning techniques, verification mechanisms, and potential attacks. We highlight emerging challenges and prospective research directions, aiming to provide valuable resources for integrating privacy, equity, and resilience into machine learning systems and help them “learn to unlearn.”

Cited by

• The Frontier of Data Erasure: A Survey on Machine Unlearning for Large Language Models
• Selective Forgetting in Option Calibration: An Operator-Theoretic Gauss-Newton Framework
• Factor Decorrelation Enhanced Data Removal from Deep Predictive Models
• Causal Fuzzing for Verifying Machine Unlearning
• CUFG: Curriculum Unlearning Guided by the Forgetting Gradient
• The End Of Universal Lifelong Identifiers: Identity Systems For The AI Era

Related

• Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects
• Machine Unlearning: A Comprehensive Survey
• Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy
• Learn to Unlearn: A Survey on Machine Unlearning
• Threats, Attacks, and Defenses in Machine Unlearning: A Survey