mlsanityData to 7 Oct 2026

A Survey on Federated Unlearning: Challenges and Opportunities

arXiv 2403.02437 ↗First posted 4 Mar 2024cs.LG cs.AI cs.DCcited by 0

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

Abstract (arXiv)

Federated learning (FL), introduced in 2017, facilitates collaborative learning between non-trusting parties with no need for the parties to explicitly share their data among themselves. This allows training models on user data while respecting privacy regulations such as GDPR and CPRA. However, emerging privacy requirements may mandate model owners to be able to forget some learned data, e.g., when requested by data owners or law enforcement. This has given birth to an active field of research called machine unlearning. In the context of FL, many techniques developed for unlearning in centralized settings are not trivially applicable! This is due to the unique differences between centralized and distributed learning, in particular, interactivity, stochasticity, heterogeneity, and limited accessibility in FL. In response, a recent line of work has focused on developing unlearning mechanisms tailored to FL. This SoK paper aims to take a deep look at the federated unlearning literature, with the goal of identifying research trends and challenges in this emerging field. By carefully categorizing papers published on FL unlearning (since 2020), we aim to pinpoint the unique complexities of federated unlearning, highlighting limitations on directly applying centralized unlearning methods. We compare existing federated unlearning methods regarding influence removal and performance recovery, compare their threat models and assumptions, and discuss their implications and limitations. For instance, we analyze the experimental setup of FL unlearning studies from various perspectives, including data heterogeneity and its simulation, the datasets used for demonstration, and evaluation metrics. Our work aims to offer insights and suggestions for future research on federated unlearning.

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 42 of its 118 references that are in the map. First posted on arXiv 4 Mar 2024.

Builds on

42 of 118 references.

Closest ancestors · 22

Same direction, newest first

  1. 2024BlockFUL: Enabling Unlearning in Blockchained Federated Learning26 Feb
  2. 2024Federated Unlearning: a Perspective of Stability and Fairness2 Feb
  3. 2024Scalable Federated Unlearning via Isolated and Coded Sharding29 Jan
  4. 2024Blockchain-enabled Trustworthy Federated Unlearning29 Jan
  5. 2024How to Forget Clients in Federated Online Learning to Rank?24 Jan
  6. 2024Communication Efficient and Provable Federated Unlearning19 Jan
  7. 2024Federated Unlearning for Human Activity Recognition17 Jan
  8. 2024Federated Unlearning: A Survey on Methods, Design Guidelines, and Evaluation Metrics10 Jan
  9. 2023SecureCut: Federated Gradient Boosting Decision Trees with Efficient Machine Unlearning22 Nov
  10. 2023A Survey on Federated Unlearning: Challenges, Methods, and Future Directions31 Oct
  11. 2023FRAMU: Attention-based Machine Unlearning using Federated Reinforcement Learning19 Sep
  12. 2023Subspace based Federated Unlearning24 Feb
10 more
  1. 2023Heterogeneous Federated Knowledge Graph Embedding Learning and Unlearning4 Feb
  2. 2022SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization21 Nov
  3. 2022Machine Unlearning of Federated Clusters28 Oct
  4. 2022Compressed Particle-Based Federated Bayesian Learning and Unlearning14 Sep
  5. 2022Federated Unlearning: How to Efficiently Erase a Client in FL?12 Jul
  6. 2022FedHarmony: Unlearning Scanner Bias with Distributed Data31 May
  7. 2022VeriFi: Towards Verifiable Federated Unlearning25 May
  8. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retraining14 Mar
  9. 2021Forget-SVGD: Particle-Based Bayesian Federated Unlearning23 Nov
  10. 2021Federated Unlearning via Class-Discriminative Pruning22 Oct

Other references · 20

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Advances and Open Problems in Federated Learningcited by 3,021
  3. 2018Federated Learning with Non-IID Datacited by 1,099
  4. 2019Machine Unlearningcited by 1,020
  5. 2018How To Backdoor Federated Learningcited by 745
  6. 2018Byzantine-Robust Distributed Learning: Towards Optimal Statistical Ratescited by 698
  7. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 566
  8. 2019Local Model Poisoning Attacks to Byzantine-Robust Federated Learningcited by 479
  9. 2020Amnesiac Machine Learningcited by 305
  10. 2022A Survey of Machine Unlearningcited by 298
  11. 2021Unlearnable Examples: Making Personal Data Unexploitablecited by 188
  12. 2022Neurotoxin: Durable Backdoors in Federated Learningcited by 97
8 more
  1. 2022Deep Unlearning via Randomized Conditionally Independent Hessianscited by 83
  2. 2020Learn to Forget: Machine Unlearning via Neuron Maskingcited by 56
  3. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 53
  4. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  5. 2022Federated Unlearning for On-Device Recommendationcited by 39
  6. 2023Get Rid Of Your Trail: Remotely Erasing Backdoors in Federated Learningcited by 12
  7. 2023On Knowledge Editing in Federated Learning: Perspectives, Challenges, and Future Directionscited by 3
  8. 2023Heterogeneous Decentralized Machine Unlearning with Seed Model Distillationcited by 3

Built on by

Not cited yet.