paper-with-me

홈 › Papers

Subspace based Federated Unlearning

2023-02-24 · Guanghao Li, Li Shen, Yan Sun, Yue Hu, Han Hu, DaCheng Tao

Federated learning (FL) enables multiple clients to train a machine learning model collaboratively without exchanging their local data. Federated unlearning is an inverse FL process that aims to remove a specified target client's contribution in FL to satisfy the user's right to be forgotten. Most existing federated unlearning algorithms require the server to store the history of the parameter updates, which is not applicable in scenarios where the server storage resource is constrained. In this paper, we propose a simple-yet-effective subspace based federated unlearning method, dubbed SFU, that lets the global model perform gradient ascent in the orthogonal space of input gradient spaces formed by other clients to eliminate the target client's contribution without requiring additional storage. Specifically, the server first collects the gradients generated from the target client after performing gradient ascent, and the input representation matrix is computed locally by the remaining clients. We also design a differential privacy method to protect the privacy of the representation matrix. Then the server merges those representation matrices to get the input gradient subspace and updates the global model in the orthogonal subspace of the input gradient subspace to complete the forgetting task with minimal model performance degradation. Experiments on MNIST, CIFAR10, and CIFAR100 show that SFU outperforms several state-of-the-art (SOTA) federated unlearning algorithms by a large margin in various settings.

📄 PDF Abstract BibTeX arXiv:2302.12448

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

EASE: Federated Multimodal Unlearning via Entanglement-Aware Anchor Closure

2026-05-01 · Zihao Ding, Beining Wu, Jun Huang arxiv

Federated Multimodal Learning (FML) trains multimodal models across decentralized clients while keeping their image-text pairs private. However, joint embedding training entangles forgotten knowledge across both modaliti…

Towards Federated Domain Unlearning: Verification Methodologies and Challenges

2024-06-05 · Kahou Tam, Kewei Xu, Li Li, Huazhu Fu

Federated Learning (FL) has evolved as a powerful tool for collaborative model training across multiple entities, ensuring data privacy in sensitive sectors such as healthcare and finance. However, the introduction of th…

Federated LearningSpecificity

Exploring Federated Unlearning: Review, Comparison, and Insights

2023-10-30 · Yang Zhao, Jiaxi Yang, Yiling Tao, Lixu Wang 외

The increasing demand for privacy-preserving machine learning has spurred interest in federated unlearning, which enables the selective removal of data from models trained in federated systems. However, developing federa…

Federated LearningPrivacy PreservingSurvey

Rethinking Federated Unlearning via the Lens of Memorization

2026-05-23 · Jiaheng Wei, Yanjun Zhang, He Zhang, Leo Yu Zhang 외 arxiv

Federated learning (FL) increasingly needs machine unlearning to comply with privacy regulations. However, existing federated unlearning approaches may overlook the overlapping information between the unlearning and rema…

Federated Learning

Forgetting to Witness: Efficient Federated Unlearning and Its Visible Evaluation

2026-04-06 · Houzhe Wang, Xiaojie Zhu, Chi Chen arxiv

With the increasing importance of data privacy and security, federated unlearning has emerged as a novel research field dedicated to ensuring that federated learning models no longer retain or leak relevant information o…

Knowledge DistillationFederated Learning