Adaptive Memory Replay for Continual Learning

arXiv:2404.12526v1 Announce Type: new
Abstract: Foundation Models (FMs) have become the hallmark of modern AI, however, these models are trained on massive data, leading to financially expensive training. Updating FMs as new data becomes available is important, however, can lead to `catastrophic forgetting', where models underperform on tasks related to data sub-populations observed too long ago. This continual learning (CL) phenomenon has been extensively studied, but primarily in a setting where only a small amount of past data can be …

abstract arxiv become catastrophic forgetting continual cs.cl cs.cv cs.lg data foundation hallmark however massive memory modern modern ai tasks training type