Forget Self-Leverage
A type of leverage matrix that characterizes the projection strength of forgotten samples themselves under the geometry of the retrained model, used to analyze the output-space gap in machine unlearning.
Timeline (last 90 days)
Two leverage matrices emerge in the framework: forget self-leverage and retain cross-leverage, capturing the entanglement of forget and retain data, respectively, under the geometry of the retrained model.
These two leverage matrices are shown both theoretically and experimentally to drive the influence of the unlearning residual on forget outputs and retain outputs.
All Facts (2)
Two leverage matrices emerge in the framework: forget self-leverage and retain cross-leverage, capturing the entanglement of forget and retain data, respectively, under the geometry of the retrained model.
50%UnverifiedThese two leverage matrices are shown both theoretically and experimentally to drive the influence of the unlearning residual on forget outputs and retain outputs.
50%