New method efficiently removes client data from federated learning models

Researchers have developed a new method called HF-KCU to efficiently remove a client's data contribution from federated learning models, addressing the computational burden of retraining. This approach approximates the influence function using Krylov subspace iterations, significantly reducing complexity and speeding up the process. A causal weighting mechanism ensures that only clients affected by the data deletion are updated, preserving model quality and enhancing privacy restoration, as demonstrated by membership inference attack success rates matching a retrained model. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enables more efficient and privacy-preserving data deletion in federated learning systems.

RANK_REASON The cluster contains an academic paper detailing a new method for a specific machine learning task. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• CIFAR-10
• Fashion-MNIST
• Federated learning
• HF-KCU
• MNIST
• ResNet-18

• paper
• safety