Calibration of Continual Learning Models

arXiv:2404.07817v1 Announce Type: new
Abstract: Continual Learning (CL) focuses on maximizing the predictive performance of a model across a non-stationary stream of data. Unfortunately, CL models tend to forget previous knowledge, thus often underperforming when compared with an offline model trained jointly on the entire data stream. Given that any CL model will eventually make mistakes, it is of crucial importance to build calibrated CL models: models that can reliably tell their confidence when making a prediction. Model calibration is …

abstract arxiv continual cs.ai cs.lg data data stream eventually knowledge offline performance predictive type will