mlsanityData to 7 Oct 2026

Multi-Class Unlearning for Image Classification via Weight Filtering

arXiv 2304.02049 ↗First posted 4 Apr 2023cs.CV cs.AI cs.LGcited by 4

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine Unlearning is an emerging paradigm for selectively removing the impact of training datapoints from a network. Unlike existing methods that target a limited subset or a single class, our framework unlearns all classes in a single round. We achieve this by modulating the network's components using memory matrices, enabling the network to demonstrate selective unlearning behavior for any class after training. By discovering weights that are specific to each class, our approach also recovers a representation of the classes which is explainable by design. We test the proposed framework on small- and medium-scale image classification datasets, with both convolution- and Transformer-based backbones, showcasing the potential for explainable solutions through unlearning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 15 of its 20 references that are in the map. First posted on arXiv 4 Apr 2023.

Builds on

15 of 20 references.

Closest ancestors · 3

Same direction, newest first

  1. 2022A Survey of Machine Unlearning6 Sep
  2. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher17 May
  3. 2021Fast Yet Effective Machine Unlearning17 Nov

Other references · 12

  1. 2019Machine Unlearningcited by 1,020
  2. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  3. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  4. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  5. 2021Knowledge distillation: A good teacher is patient and consistentcited by 255
  6. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  7. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  8. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  9. 2020Variational Bayesian Unlearningcited by 114
  10. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 89
  11. 2022HINT: Hierarchical Neuron Concept Explainercited by 17
  12. 2020Selective Forgetting of Deep Networks at a Finer Level than Samplescited by 12

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 0; 2025: 3.

4 papers.

  1. 2025Hyperbolic Safety-Aware Vision-Language Modelscited by 17
  2. 2023Safe-CLIP: Removing NSFW Concepts from Vision-and-Language Modelscited by 11
  3. 2025On the Necessity of Output Distribution Reweighting for Effective Class Unlearningcited by 3
  4. 2025Grokked Models are Better Unlearnerscited by 0