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

arXiv: https://arxiv.org/abs/2405.18040 · HTML: https://mlsanity.com/paper/2405.18040/

## Key facts

- Cited by 8 papers in the map (data through 14 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.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)

## Builds on (most cited first, 24 of 24)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [MedMNIST v2 -- A large-scale lightweight benchmark for 2D and 3D biomedical image classification](https://mlsanity.com/paper/2110.14795/) (2021)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Federated Learning on Non-IID Data Silos: An Experimental Study](https://mlsanity.com/paper/2102.02079/) (2021)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Attack of the Tails: Yes, You Really Can Backdoor Federated Learning](https://mlsanity.com/paper/2007.05084/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [Deep Unlearning via Randomized Conditionally Independent Hessians](https://mlsanity.com/paper/2204.07655/) (2022)
- [Federated Unlearning with Knowledge Distillation](https://mlsanity.com/paper/2201.09441/) (2022)
- [MPAF: Model Poisoning Attacks to Federated Learning based on Fake Clients](https://mlsanity.com/paper/2203.08669/) (2022)
- [Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers](https://mlsanity.com/paper/2301.11578/) (2023)
- [Privacy-Preserving Machine Learning with Fully Homomorphic Encryption for Deep Neural Network](https://mlsanity.com/paper/2106.07229/) (2021)
- [FedLab: A Flexible Federated Learning Framework](https://mlsanity.com/paper/2107.11621/) (2021)
- [Communication-Efficient Adaptive Federated Learning](https://mlsanity.com/paper/2205.02719/) (2022)
- [Nonconvex Variance Reduced Optimization with Arbitrary Sampling](https://mlsanity.com/paper/1809.04146/) (2018)
- [Example-based Explanations with Adversarial Attacks for Respiratory Sound Analysis](https://mlsanity.com/paper/2203.16141/) (2022)
- [Detecting Rumours with Latency Guarantees using Massive Streaming Data](https://mlsanity.com/paper/2205.06580/) (2022)
- [Model-Agnostic and Diverse Explanations for Streaming Rumour Graphs](https://mlsanity.com/paper/2207.08098/) (2022)
- [Class-wise Federated Unlearning: Harnessing Active Forgetting with Teacher-Student Memory Generation](https://mlsanity.com/paper/2307.03363/) (2023)
- [A Survey of Privacy-Preserving Model Explanations: Privacy Risks, Attacks, and Countermeasures](https://mlsanity.com/paper/2404.00673/) (2024)

## Built on by (most cited first, 8 of 8)

- [Handling Heterophily in Recommender Systems with Wavelet Hypergraph Diffusion](https://mlsanity.com/paper/2501.14399/) (2025)
- [Hypergraph Diffusion for High-Order Recommender Systems](https://mlsanity.com/paper/2501.16722/) (2025)
- [Model-Free Counterfactual Subset Selection at Scale](https://mlsanity.com/paper/2502.08326/) (2025)
- [From Privacy to Trust in the Agentic Era: A Taxonomy of Challenges in Trustworthy Federated Learning Through the Lens of Trust Report 2.0](https://mlsanity.com/paper/2507.15796/) (2025)
- [f-FUM: Federated Unlearning via min--max and f-divergence](https://mlsanity.com/paper/2602.06187/) (2026)
- [Empowering Contrastive Federated Sequential Recommendation with LLMs](https://mlsanity.com/paper/2602.09306/) (2026)
- [FINER-SQL: Boosting Small Language Models for Text-to-SQL](https://mlsanity.com/paper/2605.03465/) (2026)
- [Priority-Aware Learning-Unlearning Correction for Dynamic Decentralized LoRA Fine-Tuning](https://mlsanity.com/paper/2606.22878/) (2026)

## 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.