HF-KCU approximates influence reversal in federated learning using Krylov subspace conjugate gradients and causal weighting to achieve efficient unlearning with bounded adversarial robustness.
We measure KLoutput =E x∼Dtest DKL pretrain(· |x)∥p unlearn(· |x)
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 in federated learning using Krylov subspace conjugate gradients and causal weighting to achieve efficient unlearning with bounded adversarial robustness.