AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Federated Unlearning with Gradient Adaptive Shaping

Siyin Huang, Yufan Liao, Yuelin Du, Yu Zhang

NeurIPS 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated prompt and LoRA tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Proposes a federated unlearning method that stabilizes unlearning at both client and server stages to preserve utility of remaining clients.

Problem

Removing a specific client's influence from a trained federated global model without full retraining, while preserving utility of the remaining clients; existing approaches are unstable at client and server stages.

Approach

Stabilizes federated unlearning by shaping local forgetting updates (client side) and server-side aggregation so that unlearning does not destabilize optimization; specific mechanism not stated in the available abstract.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy