首页 > AI前沿 > DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning

DISCERN: Distributional Synthetic Replay for Retain-Free Incremental Machine Unlearning

arXiv机器学习 2026-11-05 20:11 13 阅读 查看原文

Machine unlearning aims to remove the influence of specific training data from a trained model without retraining from scratch. In real deployments, however, deletion requests arrive over time, calling for incremental class unlearning (ICU): classes are removed sequentially, previously forgotten knowledge must remain forgotten, and the remaining classes must be preserved. We present DIstributional SynthetiC rEplay for Retain-free iNcremental unlearning (DISCERN), an intervention-based class unlearning method that replaces access to the retain set with synthetic embeddings sampled from per-class parametric distributions.

Unlike prototype-based replay, which assumes an isotropic Gaussian around each class centroid, DISCERN fits Euclidean (Gaussian, Laplace, Student's $t$) and directional (von Mises--Fisher, Fisher--B