mlsanityData to 7 Oct 2026

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

arXiv 2602.06187 ↗First posted 5 Feb 2026cs.LGcited by 0

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

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.

Key facts. No citing papers in the map yet (data through 7 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.

Builds on

36 of 63 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025NoT: Federated Unlearning via Weight Negation7 Mar
  2. 2024Enable the Right to be Forgotten with Federated Client Unlearning in Medical Imaging2 Jul
  3. 2024Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience28 May
  4. 2024Unlearning during Learning: An Efficient Federated Machine Unlearning Method24 May
  5. 2024Goldfish: An Efficient Federated Unlearning Framework4 Apr
  6. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics10 Jan
  7. 2023QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation27 Nov
  8. 2023Subspace based Federated Unlearning24 Feb
  9. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
  10. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  11. 2022Federated Unlearning with Knowledge Distillation24 Jan

Other references · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2022Generative Adversarial Networkscited by 5,603
  3. 2016Optimization Methods for Large-Scale Machine Learningcited by 1,140
  4. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  5. 2013Stochastic First- and Zeroth-order Methods for Nonconvex Stochastic Programmingcited by 716
  6. 2019Certified Data Removal from Machine Learning Modelscited by 512
  7. 2016f-GAN: Training Generative Neural Samplers using Variational Divergence Minimizationcited by 504
  8. 2021Remember What You Want to Forget: Algorithms for Machine Unlearningcited by 360
  9. 2018Learning Models with Uniform Performance via Distributionally Robust Optimizationcited by 334
  10. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  11. 2021Unrolling SGD: Understanding Factors Influencing Machine Unlearningcited by 274
  12. 2020Variational Bayesian Unlearningcited by 114
13 more
  1. 2024Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacycited by 78
  2. 2024LLM Unlearning via Loss Adjustment with Only Forget Datacited by 71
  3. 2020Learn to Forget: Machine Unlearning via Neuron Maskingcited by 56
  4. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 53
  5. 2022Federated Unlearning for On-Device Recommendationcited by 39
  6. 2024Machine Unlearning: Taxonomy, Metrics, Applications, Challenges, and Prospectscited by 28
  7. 2024Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Imagescited by 18
  8. 2024Attribute-to-Delete: Machine Unlearning via Datamodel Matchingcited by 18
  9. 2025Loss Functions and Operators Generated by f-Divergencescited by 10
  10. 2024f-Divergence Based Classification: Beyond the Use of Cross-Entropycited by 8
  11. 2024Understanding Fine-tuning in Approximate Unlearning: A Theoretical Perspectivecited by 5
  12. 2024Robust Semi-supervised Learning via f-Divergence and α-R'enyi Divergencecited by 3
  13. 2024Learning to Forget using Hypernetworkscited by 3

Built on by

Not cited yet.