AI RESEARCH

Exact Federated Continual Unlearning for Ridge Heads on Frozen Foundation Models

arXiv CS.LG

ArXi:2603.12977v1 Announce Type: new Foundation models are commonly deployed as frozen feature extractors with a small trainable head to adapt to private, user-generated data in federated settings. The ``right to be forgotten'' requires removing the influence of specific samples or users from the trained model on demand. Existing federated unlearning methods target general deep models and rely on approximate reconstruction or selective re