mlsanityData to 14 Oct 2026

Orthogonal Soft Pruning for Efficient Class Unlearning

arXiv 2506.19891 ↗First posted 24 Jun 2025cs.LG cs.AIcited by 0

On the map: LLM safety and security → Federated unlearning and poisoning

Abstract (arXiv)

Efficient and controllable data unlearning in federated learning remains challenging, due to the trade-off between forgetting and retention performance. Especially under non-independent and identically distributed (non-IID) settings, where deep feature entanglement exacerbates this dilemma. To address this challenge, we propose FedOrtho, a federated unlearning framework that combines orthogonalized deep convolutional kernels with an activation-driven controllable one-shot soft pruning (OSP) mechanism. FedOrtho enforces kernel orthogonality and local-global alignment to decouple feature representations and mitigate client drift. This structural independence enables precise one-shot pruning of forgetting-related kernels while preserving retained knowledge. FedOrtho achieves SOTA performance on CIFAR-10, CIFAR100 and TinyImageNet with ResNet and VGG frameworks, verifying that FedOrtho supports class-, client-, and sample-level unlearning with over 98% forgetting quality. It reduces computational and communication costs by 2-3 orders of magnitude in federated settings and achieves subsecond-level erasure in centralized scenarios while maintaining over 97% retention accuracy and mitigating membership inference risks.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 25 of its 37 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

25 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 24

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2017Understanding Black-box Predictions via Influence Functionscited by 1,741
  6. 2019Machine Unlearningcited by 1,061
  7. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  8. 2019Certified Data Removal from Machine Learning Modelscited by 535
  9. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  10. 2023SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generationcited by 386
  11. 2022A Survey of Machine Unlearningcited by 312
  12. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 311
12 more
  1. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  2. 2021Fast Yet Effective Machine Unlearningcited by 217
  3. 2022Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teachercited by 194
  4. 2016Clipper: A Low-Latency Online Prediction Serving Systemcited by 191
  5. 2023Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampeningcited by 181
  6. 2023Boundary Unlearningcited by 134
  7. 2019Orthogonal Convolutional Neural Networkscited by 123
  8. 2020Serving DNNs like Clockwork: Performance Predictability from the Bottom Upcited by 120
  9. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 67
  10. 2017All You Need is Beyond a Good Init: Exploring Better Solution for Training Extremely Deep Convolutional Neural Networks with Orthonormality and Modulationcited by 58
  11. 2019DenseNet Models for Tiny ImageNet Classificationcited by 17
  12. 2023ERASER: Machine Unlearning in MLaaS via an Inference Serving-Aware Approachcited by 15

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation
  2. 2026Jellyfish: Zero-Shot Federated Unlearning Scheme with Knowledge Disentanglement
  3. 2026Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation
  4. 2026FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
  5. 2026f-FUM: Federated Unlearning via min--max and f-divergence
  6. 2025Certifying the Right to Be Forgotten: Primal-Dual Optimization for Sample and Label Unlearning in Vertical Federated Learning
  7. 2023Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
  8. 2026Rethinking Federated Unlearning via the Lens of Memorization