Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening

arXiv:2402.10098v1 Announce Type: new
Abstract: Data entry constitutes a fundamental component of the machine learning pipeline, yet it frequently results in the introduction of labelling errors. When a model has been trained on a dataset containing such errors its performance is reduced. This leads to the challenge of efficiently unlearning the influence of the erroneous data to improve the model performance without needing to completely retrain the model. While model editing methods exist for cases in which the correct label …

abstract arxiv challenge cs.lg data data entry dataset error errors free free data introduction labelling leads machine machine learning performance pipeline type unlearning