✓ arXivTechnology & Tools
Why deleting data can fail in agent networks
The study shows deleted data can still echo through later training rounds in self-improving federated agent networks.
The paper argues that unlearning gets harder when agents keep training after deployment. If a data owner asks for deletion, the original data may already have shaped later trajectories that are kept.
The authors say that influence can survive retraining, grow with more forget-shaped data, and be traced through deployment, collection, and aggregation records.
Why it mattersIt raises the cost and complexity of data deletion in systems that keep learning after launch.
Open this story in InSnip →
