pith. sign in

Early approaches of machine unlearning focused on exact unlearning, which requires retraining the model from scratch after excluding the forget set (Bourtoule et al., 2021)

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

fields

cs.LG 1

years

2025 1

verdicts

UNVERDICTED 1

representative citing papers

OFMU: Optimization-Driven Framework for Machine Unlearning

cs.LG · 2025-09-26 · unverdicted · novelty 6.0

A penalty-based bi-level optimization framework for machine unlearning that decorrelates forget and retention gradients via inner maximization and restores utility via outer minimization, with convergence guarantees and improved trade-offs on vision and language benchmarks.

citing papers explorer

Showing 1 of 1 citing paper.

  • OFMU: Optimization-Driven Framework for Machine Unlearning cs.LG · 2025-09-26 · unverdicted · none · ref 27

    A penalty-based bi-level optimization framework for machine unlearning that decorrelates forget and retention gradients via inner maximization and restores utility via outer minimization, with convergence guarantees and improved trade-offs on vision and language benchmarks.