AFU-IC
Cross-source consensus on AFU-IC from 1 sources and 4 claims.
1 sources · 4 claims
Uses
How it works
Benefits
Highlighted claims
- AFU-IC has two phases: local asynchronous gradient ascent and server-side invariance calibration. — Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging
- AFU-IC separates local client-side erasure from server-side structural calibration. — Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging
- AFU-IC achieved backdoor accuracy close to or below retraining while requiring much less wall-clock time across all three datasets. — Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging
- AFU-IC is presented as practical for cross-silo medical imaging settings where deletion requests must not stop the whole federation. — Asynchronous Federated Unlearning with Invariance Calibration for Medical Imaging