mlsanityData to 7 Oct 2026

Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience

arXiv 2405.18040 ↗First posted 28 May 2024cs.LG cs.AI cs.DCcited by 8

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

Abstract (arXiv)

Federated learning (FL) has recently emerged as a compelling machine learning paradigm, prioritizing the protection of privacy for training data. The increasing demand to address issues such as ``the right to be forgotten'' and combat data poisoning attacks highlights the importance of techniques, known as textitunlearning, which facilitate the removal of specific training data from trained FL models. Despite numerous unlearning methods proposed for centralized learning, they often prove inapplicable to FL due to fundamental differences in the operation of the two learning paradigms. Consequently, unlearning in FL remains in its early stages, presenting several challenges. Many existing unlearning solutions in FL require a costly retraining process, which can be burdensome for clients. Moreover, these methods are primarily validated through experiments, lacking theoretical assurances. In this study, we introduce Fast-FedUL, a tailored unlearning method for FL, which eliminates the need for retraining entirely. Through meticulous analysis of the target client's influence on the global model in each round, we develop an algorithm to systematically remove the impact of the target client from the trained model. In addition to presenting empirical findings, we offer a theoretical analysis delineating the upper bound of our unlearned model and the exact retrained model (the one obtained through retraining using untargeted clients). Experimental results with backdoor attack scenarios indicate that Fast-FedUL effectively removes almost all traces of the target client, while retaining the knowledge of untargeted clients (obtaining a high accuracy of up to 98% on the main task). Significantly, Fast-FedUL attains the lowest time complexity, providing a speed that is 1000 times faster than retraining. Our source code is publicly available at urlhttps://github.com/thanhtrunghuynh93/fastFedUL.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Placed in Federated unlearning and poisoning, one of 12 directions in LLM safety and security. Builds on 24 of its 42 references that are in the map. First posted on arXiv 28 May 2024.

Builds on

24 of 42 references.

Closest ancestors · 5

Same direction, newest first

  1. 2023Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation7 Jul
  2. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
  3. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  4. 2022Federated Unlearning with Knowledge Distillation24 Jan
  5. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 19

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Machine Unlearningcited by 1,020
  3. 2021MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classificationcited by 682
  4. 2019Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networkscited by 599
  5. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  6. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 307
  7. 2022A Survey of Machine Unlearningcited by 298
  8. 2020DeltaGrad: Rapid retraining of machine learning modelscited by 143
  9. 2022Deep Unlearning via Randomized Conditionally Independent Hessianscited by 83
  10. 2023Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifierscited by 66
  11. 2022MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clientscited by 65
  12. 2021Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Networkcited by 57
7 more
  1. 2022Communication-Efficient Adaptive Federated Learningcited by 55
  2. 2021FedLab: A Flexible Federated Learning Frameworkcited by 54
  3. 2018Nonconvex Variance Reduced Optimization with Arbitrary Samplingcited by 14
  4. 2022Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysiscited by 13
  5. 2022Detecting Rumours with Latency Guarantees using Massive Streaming Datacited by 12
  6. 2022Model-Agnostic and Diverse Explanations for Streaming Rumour Graphscited by 9
  7. 2024A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasurescited by 6

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 4.

8 papers.

  1. 2025Handling Heterophily in Recommender Systems with Wavelet Hypergraph Diffusioncited by 1
  2. 2025Hypergraph Diffusion for High-Order Recommender Systemscited by 0
  3. 2025Model-Free Counterfactual Subset Selection at Scalecited by 0
  4. 2025From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0cited by 0
  5. 2026f-FUM: Federated Unlearning via min--max and f-divergencecited by 0
  6. 2026Empowering Contrastive Federated Sequential Recommendation with LLMscited by 0
  7. 2026FINER-SQL: Boosting Small Language Models for Text-to-SQLcited by 0
  8. 2026Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuningcited by 0