mlsanityData to 7 Oct 2026

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization

arXiv 2211.11656 ↗First posted 21 Nov 2022cs.LGcited by 16

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

Abstract (arXiv)

Machine Unlearning (MU) is an increasingly important topic in machine learning safety, aiming at removing the contribution of a given data point from a training procedure. Federated Unlearning (FU) consists in extending MU to unlearn a given client's contribution from a federated training routine. While several FU methods have been proposed, we currently lack a general approach providing formal unlearning guarantees to the FedAvg routine, while ensuring scalability and generalization beyond the convex assumption on the clients' loss functions. We aim at filling this gap by proposing SIFU (Sequential Informed Federated Unlearning), a new FU method applying to both convex and non-convex optimization regimes. SIFU naturally applies to FedAvg without additional computational cost for the clients and provides formal guarantees on the quality of the unlearning task. We provide a theoretical analysis of the unlearning properties of SIFU, and practically demonstrate its effectiveness as compared to a panel of unlearning methods from the state-of-the-art.

Key facts. Cited by 16 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 25 of its 46 references that are in the map. First posted on arXiv 21 Nov 2022.

Builds on

25 of 46 references.

Closest ancestors · 5

Same direction, newest first

  1. 2022Machine Unlearning of Federated Clusters28 Oct
  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. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearning23 Nov
  5. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,220
  5. 2019Machine Unlearningcited by 1,020
  6. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 897
  7. 2019Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classificationcited by 836
  8. 2018LEAF: A Benchmark for Federated Settingscited by 780
  9. 2015Train faster, generalize better: Stability of stochastic gradient descentcited by 547
  10. 2019Certified Data Removal from Machine Learning Modelscited by 512
  11. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  12. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
8 more
  1. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  2. 2020Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observationscited by 171
  3. 2021Adaptive Machine Unlearningcited by 164
  4. 2020Mixed-Privacy Forgetting in Deep Networkscited by 158
  5. 2020Understanding Gradient Clipping in Private SGD: A Geometric Perspectivecited by 140
  6. 2020Towards Probabilistic Verification of Machine Unlearningcited by 46
  7. 2021Certifiable Machine Unlearning for Linear Modelscited by 42
  8. 2020Online Forgetting Process for Linear Regression Modelscited by 21

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 7; 2025: 5; 2026: 4.

16 papers.

Sort:

By area:

  1. 2024Machine Unlearning: A Comprehensive Surveycited by 33
  2. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  3. 2024Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functionscited by 17
  4. 2025When to Forget? Complexity Trade-offs in Machine Unlearningcited by 9
  5. 2024Towards Efficient and Certified Recovery from Poisoning Attacks in Federated Learningcited by 7
  6. 2024ConDa: Fast Federated Unlearning with Contribution Dampeningcited by 2
  7. 2025Addressing Out-of-Label Hazard Detection in Dashcam Videos: Insights from the COOOL Challengecited by 2
  8. 2026Certified Unlearning in Decentralized Federated Learningcited by 2
  9. 2025BadFU: Backdoor Federated Learning through Adversarial Machine Unlearningcited by 1
  10. 2024A Survey on Federated Unlearning: Challenges and Opportunitiescited by 0
  11. 2024Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentivescited by 0
  12. 2024Federated Unlearning Model Recovery in Data with Skewed Label Distributionscited by 0
4 more
  1. 2025Descend or Rewind? Stochastic Gradient Descent Unlearningcited by 0
  2. 2026Variance-Reduced (varepsilon,δ)-Unlearning using Forget Set Gradientscited by 0
  3. 2026pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learningcited by 0
  4. 2026When Unlearning Fails: Reliable Data Deletion under Post-Training in Agent Networkscited by 0