Home Science Causal Unlearning in Collaborative Optimization: Exact...
Science

Causal Unlearning in Collaborative Optimization: Exact and Approximate Influence Reversal under Adversarial Contributions

Key Points

arXiv:2605.20341v2 Announce Type: replace Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. We present HF-KCU, a method that removes a client's contribution by approximating the influence function through conjugate gradient iterations in Krylov subspaces, reducing complexity from O(d^3) to O(kd) where k<<d. A causal weighting mechanism ensures that only...

arXiv:2605.20341v2 Announce Type: replace Abstract: Federated learning systems must support data deletion requests to comply with privacy regulations, yet retraining from scratch after each deletion is computationally prohibitive. We present HF-KCU, a method that removes a client's contribution by approximating the influence function through conjugate gradient iterations in Krylov subspaces, reducing complexity from O(d^3) to O(kd) where k<
Adversarial Contributions arXiv:2605.20341v2 Announce Type (ORG) HF-KCU (ORG) Krylov (PERSON) Hessian (ORG) MNIST (ORG) Fashion-MNIST (ORG)
Originally published by arXiv CS Read original →