30 June 2024
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 an active research topic in machine learning yet to be properly investigated in CL.
In this work, EMERGE partners from the University of Pisa provide the first empirical study of the behavior of calibration approaches in CL showing that CL strategies do not inherently learn calibrated models. To mitigate this issue the authors design a continual calibration approach that improves the performance of post-processing calibration methods over a wide range of different benchmarks and CL strategies. CL does not necessarily need perfect predictive models but rather it can benefit from reliable predictive models.
Read the paper in the link below.
More Information
