mlsanityData to 14 Oct 2026

Forgetting Through Transforming: Enabling Federated Unlearning via Class-Aware Representation Transformation

arXiv 2410.06848 ↗First posted 9 Oct 2024cs.LGcited by 0

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

Abstract (arXiv)

Federated Unlearning (FU) enables clients to selectively remove the influence of specific data from a trained federated learning model, addressing privacy concerns and regulatory requirements. However, existing FU methods often struggle to balance effective erasure with model utility preservation, especially for class-level unlearning in non-IID settings. We propose Federated Unlearning via Class-aware Representation Transformation (FUCRT), a novel method that achieves unlearning through class-aware representation transformation. FUCRT employs two key components: (1) a transformation class selection strategy to identify optimal forgetting directions, and (2) a transformation alignment technique using dual class-aware contrastive learning to ensure consistent transformations across clients. Extensive experiments on four datasets demonstrate FUCRT's superior performance in terms of erasure guarantee, model utility preservation, and efficiency. FUCRT achieves complete (100%) erasure of unlearning classes while maintaining or improving performance on remaining classes, outperforming state-of-the-art baselines across both IID and Non-IID settings. Analysis of the representation space reveals FUCRT's ability to effectively merge unlearning class representations with the transformation class from remaining classes, closely mimicking the model retrained from scratch.

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 31 of its 49 references that are in the map. First posted on arXiv 9 Oct 2024.

Builds on

31 of 49 references.

Closest ancestors · 4

Same direction, newest first

  1. 2024Unlearning during Learning: An Efficient Federated Machine Unlearning Method24 May
  2. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions31 Oct
  3. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  4. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 27

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  4. 2019Advances and Open Problems in Federated Learningcited by 3,046
  5. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  6. 2020Supervised Contrastive Learningcited by 2,829
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  8. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  9. 2019Machine Unlearningcited by 1,061
  10. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 618
  11. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 465
  12. 2023Towards Unbounded Machine Unlearningcited by 268
15 more
  1. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 255
  2. 2021No Fear of Heterogeneity: Classifier Calibration for Federated Learning with Non-IID Datacited by 241
  3. 2021Fast Yet Effective Machine Unlearningcited by 217
  4. 2021Federated Learning for Smart Healthcare: A Surveycited by 184
  5. 2021Adaptive Machine Unlearningcited by 176
  6. 2023Boundary Unlearningcited by 134
  7. 2020Machine Unlearning for Random Forestscited by 131
  8. 2021Local Learning Matters: Rethinking Data Heterogeneity in Federated Learningcited by 114
  9. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 95
  10. 2022Federated Unlearning for On-Device Recommendationcited by 43
  11. 2020Federated Unlearningcited by 29
  12. 2021Machine unlearning via GANcited by 6
  13. 2019Stochastic Channel-Based Federated Learning for Medical Data Privacy Preservingcited by 5
  14. 2022FedMCSA: Personalized Federated Learning via Model Components Self-Attentioncited by 3
  15. 2022Dual Class-Aware Contrastive Federated Semi-Supervised Learningcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025ToFU: Transforming How Federated Learning Systems Forget User Data
  2. 2023Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation
  3. 2024Streamlined Federated Unlearning: Unite as One to Be Highly Efficient
  4. 2026f-FUM: Federated Unlearning via min--max and f-divergence
  5. 2026FedCARE: Federated Unlearning with Conflict-Aware Projection and Relearning-Resistant Recovery
  6. 2026Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation
  7. 2024Towards Federated Domain Unlearning: Verification Methodologies and Challenges
  8. 2026FUPareto: Bridging the Forgetting-Utility Gap in Federated Unlearning via Pareto Augmented Optimization