Weighted Ensemble Models Are Strong Continual Learners

arXiv:2312.08977v2 Announce Type: replace
Abstract: In this work, we study the problem of continual learning (CL) where the goal is to learn a model on a sequence of tasks, such that the data from the previous tasks becomes unavailable while learning on the current task data. CL is essentially a balancing act between being able to learn on the new task (i.e., plasticity) and maintaining the performance on the previously learned concepts (i.e., stability). Intending to address the stability-plasticity trade-off, …

arxiv continual cs.ai cs.cv cs.lg ensemble type