HF-KCU approximates influence reversal for unlearning in federated learning using Krylov-subspace conjugate gradients and causal weighting, delivering 47x speedup and privacy restoration on CIFAR-10, MNIST, and Fashion-MNIST while handling bounded adversarial perturbations.
Ainsworth and Jonathan Hayase and Siddhartha Srinivasan , title =
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions
HF-KCU approximates influence reversal for unlearning in federated learning using Krylov-subspace conjugate gradients and causal weighting, delivering 47x speedup and privacy restoration on CIFAR-10, MNIST, and Fashion-MNIST while handling bounded adversarial perturbations.