English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Zendy Plus

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Zendy Tools

Zendy Open

Machine Unlearning (MU) is an increasingly important topic in machinelearning safety, aiming at removing the contribution of a given data point froma training procedure. Federated Unlearning (FU) consists in extending MU tounlearn a given client's contribution from a federated training routine. Whileseveral FU methods have been proposed, we currently lack a general approachproviding formal unlearning guarantees to the FedAvg routine, while ensuringscalability and generalization beyond the convex assumption on the clients'loss functions. We aim at filling this gap by proposing SIFU (SequentialInformed Federated Unlearning), a new FU method applying to both convex andnon-convex optimization regimes. SIFU naturally applies to FedAvg withoutadditional computational cost for the clients and provides formal guarantees onthe quality of the unlearning task. We provide a theoretical analysis of theunlearning properties of SIFU, and practically demonstrate its effectiveness ascompared to a panel of unlearning methods from the state-of-the-art.

SIFU: Sequential Informed Federated Unlearning for Efficient and Provable Client Unlearning in Federated Optimization