# f-FUM: Federated Unlearning via min--max and f-divergence

arXiv: https://arxiv.org/abs/2602.06187 · HTML: https://mlsanity.com/paper/2602.06187/

## 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 36 of its 63 references that are in the map.
- First posted on arXiv 5 Feb 2026.

## Placed in

- LLM safety and security / [Federated unlearning and poisoning](https://mlsanity.com/safety/federated-unlearning-and-poisoning/)
- Knowledge distillation / [Federated, robust and private distillation](https://mlsanity.com/distill/federated-robust-and-private-distillation/)

## Builds on (most cited first, 30 of 36)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Generative Adversarial Networks](https://mlsanity.com/paper/2203.00667/) (2022)
- [Optimization Methods for Large-Scale Machine Learning](https://mlsanity.com/paper/1606.04838/) (2016)
- [BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chain](https://mlsanity.com/paper/1708.06733/) (2017)
- [Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programming](https://mlsanity.com/paper/1309.5549/) (2013)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [f-GAN: Training Generative Neural Samplers using Variational Divergence Minimization](https://mlsanity.com/paper/1606.00709/) (2016)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Learning Models with Uniform Performance via Distributionally Robust Optimization](https://mlsanity.com/paper/1810.08750/) (2018)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining](https://mlsanity.com/paper/2203.07320/) (2022)
- [Variational Bayesian Unlearning](https://mlsanity.com/paper/2010.12883/) (2020)
- [Federated Unlearning: How to Efficiently Erase a Client in FL?](https://mlsanity.com/paper/2207.05521/) (2022)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [LLM Unlearning via Loss Adjustment with Only Forget Data](https://mlsanity.com/paper/2410.11143/) (2024)
- [Federated Unlearning with Knowledge Distillation](https://mlsanity.com/paper/2201.09441/) (2022)
- [Learn to Forget: Machine Unlearning via Neuron Masking](https://mlsanity.com/paper/2003.10933/) (2020)
- [FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Information](https://mlsanity.com/paper/2210.10936/) (2022)
- [Federated Unlearning for On-Device Recommendation](https://mlsanity.com/paper/2210.10958/) (2022)
- [Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospects](https://mlsanity.com/paper/2403.08254/) (2024)
- [Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics](https://mlsanity.com/paper/2401.05146/) (2024)
- [Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images](https://mlsanity.com/paper/2404.12922/) (2024)
- [Attribute-to-Delete: Machine Unlearning via Datamodel Matching](https://mlsanity.com/paper/2410.23232/) (2024)
- [Subspace based Federated Unlearning](https://mlsanity.com/paper/2302.12448/) (2023)
- [NoT: Federated Unlearning via Weight Negation](https://mlsanity.com/paper/2503.05657/) (2025)
- [Unlearning during Learning: An Efficient Federated Machine Unlearning Method](https://mlsanity.com/paper/2405.15474/) (2024)
- [QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation](https://mlsanity.com/paper/2311.15603/) (2023)
- [Loss Functions and Operators Generated by f-Divergences](https://mlsanity.com/paper/2501.18537/) (2025)
- [Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging](https://mlsanity.com/paper/2407.02356/) (2024)

## Abstract (arXiv)

Federated learning (FL) enables collaborative training while keeping raw data on clients. Deletion requests and the discovery of poisoned data create a need to remove selected contributions from an already trained model. This is challenging in FL because client data are decentralized and their influence is entangled through repeated aggregation. We present f-FUM, an active federated unlearning method that builds on teacher-student forget/retain optimization. Starting from a pretrained global model, the method keeps that model fixed as a teacher. Clients maximize an f-divergence between student and teacher predictive distributions on forget examples, then minimize KL-based teacher-student disagreement and supervised loss on retained examples. The updates are aggregated in separate, sample-weighted synchronization phases without moving raw data to the server or changing the model architecture. We evaluate forget-side divergence choices in client-level and data-level deletion settings involving backdoors, label confusion, and clean-data deletion. Under equal synchronization-phase budgets, divergence choice changes the forgetting-utility trade-off, yielding improvements in some settings and mixed results in others. In the evaluated configurations, f-FUM uses up to 8 times fewer synchronization phases than full federated retraining.