AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Efficient Knowledge Deletion from Trained Models Through Layer-wise Partial Machine Unlearning

Vinay Chakravarthi Gogineni, Esmaeil S. Nadimi

JMLR 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Parameter-efficient transfer analysis · 2 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add layer-wise pruning of stored updates (partial amnesiac unlearning)Amnesiac unlearning, MLP · MNIST (unlearn class 3)accuracy on retained data (%): 51.93 -> 94.47Improved
add layer-wise pruning of stored updates (partial amnesiac unlearning)Amnesiac unlearning, ResNet9 · MNIST (unlearn class 3)accuracy on retained data (%): 68.04 -> 98.33Improved
add layer-wise pruning of stored updates (partial amnesiac unlearning)Amnesiac unlearning, AlexNet · OrganAMNIST (unlearn class 3)accuracy on retained data (%): 9.90 -> 80.44Improved
add layer-wise pruning of stored updates (partial amnesiac unlearning)Amnesiac unlearning, ConvNet · OrganAMNIST (unlearn class 3)accuracy on retained data (%): 16.66 -> 75.20Improved
add layer-wise partial updates to label-flipping unlearningLabel-flipping unlearning, LeNet · MNIST (unlearn class 3)accuracy on retained data (%): 86.61 -> 90.62Improved
add layer-wise partial updates to label-flipping unlearningLabel-flipping unlearning, ResNet9 · OrganAMNIST (unlearn class 3)accuracy on retained data (%): 76.93 -> 82.27Improved
add layer-wise partial updates to optimization-based unlearningOptimization-based unlearning, FCNN · MNIST (unlearn class 3)accuracy on retained data (%): 85.12 -> 91.36Improved
add layer-wise partial updates to optimization-based unlearningOptimization-based unlearning, ResNet9 · OrganAMNIST (unlearn class 3)accuracy on retained data (%): 76.93 -> 85.89Improved
add layer-wise partial updates to optimization-based unlearningOptimization-based unlearning, ResNet9 · MNIST (unlearn class 3)accuracy on retained data (%): 97.33 -> 97.93No clear effect
add layer-wise partial updates to label-flipping unlearningLabel-flipping unlearning, ResNet9 · MNIST (unlearn class 3)accuracy on retained data (%): 97.28 -> 97.88No clear effect
add layer-wise partial updates to label-flipping unlearningLabel-flipping unlearning, AlexNet · OrganAMNIST (unlearn class 3)accuracy on retained data (%): 56.64 -> 56.33Mixed
use random layer-wise pruning with decreasing amount over depth instead of magnitude-based or global pruning (ablation)Partial amnesiac unlearning · MNIST and OrganAMNISTaccuracy on retained data (%)Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy