mlsanityData to 7 Oct 2026

PruneForget: Joint Unlearning and Pruning of Vision Models

arXiv 2609.32162 ↗First posted 26 Sep 2026cs.CVcited by 0

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

Machine unlearning and model pruning are increasingly coupled in the real world. Models must support unlearning requests, e.g., for safety concerns, while also meeting requirements in latency and memory budget. Until recently, existing works have studied each aspect as an independent problem, e.g., running unlearning and pruning sequentially. In this work, we show that unlearning and pruning are naturally aligned and should be solved jointly to be made aware of each other. Intuitively, parameters that encode information of the unlearned samples are natural pruning targets, as unlearning and pruning both call for the "deletion" of such parameters. We propose PruneForget, a method that uses the unlearn set as a guide for pruning, so that unlearning and pruning mutually benefit each other. Extensive experiments on image classifiers and generative models show that PruneForget removes the influence of the unlearned samples while producing a more compact model with reduced inference cost. It achieves a negligible performance gap relative to an oracle that retrains from scratch for unlearning and then prunes.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 57 of its 73 references that are in the map. First posted on arXiv 26 Sep 2026.

Builds on

57 of 73 references.

Closest ancestors · 14

Same direction, newest first

  1. 2026Designing to Forget: Deep Semi-parametric Models for Unlearning24 Mar
  2. 2025The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models24 Jul
  3. 2024A Closer Look at Machine Unlearning for Large Language Models10 Oct
  4. 2024Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement29 Sep
  5. 2024Revisiting Machine Unlearning with Dimensional Alignment25 Jul
  6. 2024Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning8 Apr
  7. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation19 Oct
  8. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening15 Aug
  9. 2023Model Sparsity Can Simplify Machine Unlearning11 Apr
  10. 2023Towards Unbounded Machine Unlearning20 Feb
  11. 2022Evaluating Machine Unlearning via Epistemic Uncertainty23 Aug
  12. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher17 May
2 more
  1. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearning27 Sep
  2. 2021Machine Unlearning of Features and Labels26 Aug

Other references · 43

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2021Swin Transformer: Hierarchical Vision Transformer using Shifted Windowscited by 12,082
  4. 2022Scalable Diffusion Models with Transformerscited by 5,931
  5. 2015Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Codingcited by 2,291
  6. 2018The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networkscited by 2,250
  7. 2017Understanding Black-box Predictions via Influence Functionscited by 1,714
  8. 2017Learning Efficient Convolutional Networks through Network Slimmingcited by 673
  9. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  10. 2023Erasing Concepts from Diffusion Modelscited by 530
  11. 2020Movement Pruning: Adaptive Sparsity by Fine-Tuningcited by 398
  12. 2018Filter Pruning via Geometric Median for Deep Convolutional Neural Networks Accelerationcited by 365
31 more
  1. 2020Amnesiac Machine Learningcited by 305
  2. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
  3. 2023Forget-Me-Not: Learning to Forget in Text-to-Image Diffusion Modelscited by 297
  4. 2020HRank: Filter Pruning using High-Rank Feature Mapcited by 291
  5. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 273
  6. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  7. 2017NISP: Pruning Networks using Neuron Importance Score Propagationcited by 228
  8. 2017Learning to Prune Deep Neural Networks via Layer-wise Optimal Brain Surgeoncited by 219
  9. 2023DepGraph: Towards Any Structural Pruningcited by 202
  10. 2023Structural Pruning for Diffusion Modelscited by 193
  11. 2023Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Modelscited by 175
  12. 2021Group Fisher Pruning for Practical Network Compressioncited by 130
  13. 2019Gate Decorator: Global Filter Pruning Method for Accelerating Deep Convolutional Neural Networkscited by 118
  14. 2018Rethinking the Smaller-Norm-Less-Informative Assumption in Channel Pruning of Convolution Layerscited by 112
  15. 2019A Signal Propagation Perspective for Pruning Neural Networks at Initializationcited by 96
  16. 2021Vision Transformer Pruningcited by 77
  17. 2019Centripetal SGD for Pruning Very Deep Convolutional Networks with Complicated Structurecited by 76
  18. 2020Logarithmic Pruning is All You Needcited by 71
  19. 2024LD-Pruner: Efficient Pruning of Latent Diffusion Models using Task-Agnostic Insightscited by 65
  20. 2020Lookahead: A Far-Sighted Alternative of Magnitude-based Pruningcited by 61
  21. 2024Erasing Undesirable Influence in Diffusion Modelscited by 52
  22. 2022CP-ViT: Cascade Vision Transformer Pruning via Progressive Sparsity Predictioncited by 39
  23. 2019Approximated Oracle Filter Pruning for Destructive CNN Width Optimizationcited by 35
  24. 2024Isomorphic Pruning for Vision Modelscited by 21
  25. 2024Efficient Fine-Tuning and Concept Suppression for Pruned Diffusion Modelscited by 15
  26. 2024Not All Prompts Are Made Equal: Prompt-based Pruning of Text-to-Image Diffusion Modelscited by 13
  27. 2019Parameterized Structured Pruning for Deep Neural Networkscited by 4
  28. 2025Sealing The Backdoor: Unlearning Adversarial Text Triggers In Diffusion Models Using Knowledge Distillationcited by 2
  29. 2026Collaborative Multi-Mode Pruning for Vision-Language Modelscited by 2
  30. 2026Prune Once: Retraining-Free Task-Agnostic Pruning for Vision-Language Modelscited by 1
  31. 2026Cut-ViT: Task-Specific Model Pruning via Gram Anchoring Subspace Consistencycited by 1

Built on by

Not cited yet.