Recall-Oriented Continual Learning with Generative Adversarial Meta-Model

arXiv:2403.03082v1 Announce Type: new
Abstract: The stability-plasticity dilemma is a major challenge in continual learning, as it involves balancing the conflicting objectives of maintaining performance on previous tasks while learning new tasks. In this paper, we propose the recall-oriented continual learning framework to address this challenge. Inspired by the human brain's ability to separate the mechanisms responsible for stability and plasticity, our framework consists of a two-level architecture where an inference network effectively acquires new knowledge and a generative network …

adversarial arxiv continual cs.ai cs.cv cs.lg generative meta recall type