← Back to all news
arXiv Machine Learning By Hammad Rizwan, Mahtab Sarvmaili, Hassan Sajjad, Ga Wu

Instance-Level Difficulty: A Missing Perspective in Machine Unlearning

Read the original on arXiv Machine Learning →

The paper highlights that current deep machine unlearning research focuses on overall effectiveness, neglecting how difficult it is to unlearn individual training samples. It presents a detailed instance-level performance analysis across various algorithms and datasets, identifying four factors that make unlearning a data point hard. The study shows these factors are independent of the unlearning method but depend on the target model and its training data, urging future research to consider instance-level difficulty.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Sep 30

Reference-Guided Machine Unlearning

Reference-Guided Machine Unlearning (ReGUn) is a vision unlearning framework that prioritizes distributional indistinguishability over degradation-based heuristics. It uses disjoint held-out data to create a class-conditioned reference distribution for distillation, guiding forget samples toward non-member behavior without explicitly degrading predictions. Experiments across various architectures and datasets show that ReGUn achieves a competitive forgetting–utility trade-off and closely matches retrain-like membership inference behavior.

By Jonas Mirlach, Sonia Laguna, Julia E. Vogt
efficiency
More like this →
arXiv AI
Sep 1

Forget or Fine-tune? A Comparative Study of Machine Unlearning Strategies for Noisy Label Correction

The paper compares five machine unlearning (MU) methods—NegGrad, Fine‑Tuning (FT), Random Labeling (RL), SalUn, and MUNBa—on noisy‑label correction across CIFAR‑10, CIFAR‑100, and Food‑101N. Results show that the best MU strategy depends on the noise type: FT works well for most closed‑set noise, RL and SalUn are robust and nearly match retraining accuracy under instance‑dependent noise, while MUNBa excels only under extreme symmetric noise. In open‑set noise, retraining on the cleaned data actually hurts performance, indicating that approximating retraining is not suitable in that regime, yet all MU methods still achieve near‑retraining accuracy on Food‑101N with much lower runtime.

By Jo\~ao L. P. Santana, Filipe R. Cordeiro
reinforcement-learningfine-tuning
More like this →