mlsanityData to 7 Oct 2026

Towards Robust Knowledge Removal in Federated Learning with High Data Heterogeneity

arXiv 2510.13606 ↗First posted 15 Oct 2025cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Nowdays, there are an abundance of portable devices capable of collecting large amounts of data and with decent computational power. This opened the possibility to train AI models in a distributed manner, preserving the participating clients' privacy. However, because of privacy regulations and safety requirements, elimination upon necessity of a client contribution to the model has become mandatory. The cleansing process must satisfy specific efficacy and time requirements. In recent years, research efforts have produced several knowledge removal methods, but these require multiple communication rounds between the data holders and the process coordinator. This can cause the unavailability of an effective model up to the end of the removal process, which can result in a disservice to the system users. In this paper, we introduce an innovative solution based on Task Arithmetic and the Neural Tangent Kernel, to rapidly remove a client's influence from a model.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 20 of its 32 references that are in the map. First posted on arXiv 15 Oct 2025.

Builds on

20 of 32 references.

References · 20

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,971
  4. 2018Neural Tangent Kernel: Convergence and Generalization in Neural Networkscited by 2,597
  5. 2022Editing Models with Task Arithmeticcited by 1,076
  6. 2017Remote Sensing Image Scene Classification: Benchmark and State of the Artcited by 791
  7. 2021Merging Models with Fisher-Weighted Averagingcited by 613
  8. 2021FedProto: Federated Prototype Learning across Heterogeneous Clientscited by 349
  9. 2023Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Modelscited by 218
  10. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  11. 2022The Right to be Forgotten in Federated Learning: An Efficient Realization with Rapid Retrainingcited by 109
  12. 2022FedRecover: Recovering from Poisoning Attacks in Federated Learning using Historical Informationcited by 53
8 more
  1. 2023GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgettingcited by 27
  2. 2024Closed-form merging of parameter-efficient modules for Federated Continual Learningcited by 22
  3. 2024Semantic Residual Prompts for Continual Learningcited by 19
  4. 2024A Second-Order Perspective on Model Compositionality and Incremental Learningcited by 18
  5. 2024CLIP with Generative Latent Replay: a Strong Baseline for Incremental Learningcited by 17
  6. 2025Update Your Transformer to the Latest Release: Re-Basin of Task Vectorscited by 17
  7. 2024Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivitycited by 11
  8. 2024Federated Class-Incremental Learning with Hierarchical Generative Prototypescited by 6

Built on by

Not cited yet.