Treatment Effect Estimation to Guide Model Optimization in Continual LearningDownload PDF

Published: 11 Jan 2023, Last Modified: 05 May 2023AAAI23 Bridge Continual CausalityReaders: Everyone
TL;DR: Predicting the behavior of models in Continual Learning settings using Treatment Effect Estimation
Abstract: Continual Learning systems are faced with a potentially large numbers of tasks to be learned while the models employed have only limited capacity available, which makes it potentially impossible to learn all required tasks within a single model. In order to detect on when a model might break we propose to use treatment effect estimation techniques to estimate the effect of training a model on a new task w.r.t. some suitable performance measure.
5 Replies