The Lebesgue measure of ε-forging sets decays as O(ε) or ε^d for linear models and as ε^{(d-r)/2} under mild regularity assumptions, with vanishing probability of random sampling.
Towards scalable exact machine unlearning using parameter-efficient fine-tuning
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
fields
cs.LG 3representative citing papers
MSA performs data unlearning in LLMs by arithmetic operations on prior model checkpoints to remove targeted datapoint influence, with experiments showing competitive or better results than existing unlearning methods.
XGBoost-Forget applies machine unlearning to XGBoost on IoT-23 and GeNIS network intrusion datasets, achieving faster forgetting with maintained predictive performance.
citing papers explorer
-
The Measure of Deception: An Analysis of Data Forging in Machine Unlearning
The Lebesgue measure of ε-forging sets decays as O(ε) or ε^d for linear models and as ε^{(d-r)/2} under mild regularity assumptions, with vanishing probability of random sampling.
-
Revisiting the Past: Data Unlearning with Model State History
MSA performs data unlearning in LLMs by arithmetic operations on prior model checkpoints to remove targeted datapoint influence, with experiments showing competitive or better results than existing unlearning methods.
-
Machine Unlearning for the XGBoost Model with Network Intrusion Datasets
XGBoost-Forget applies machine unlearning to XGBoost on IoT-23 and GeNIS network intrusion datasets, achieving faster forgetting with maintained predictive performance.