Overcoming Generic Knowledge Loss with Selective Parameter Update

arXiv:2308.12462v4 Announce Type: replace
Abstract: Foundation models encompass an extensive knowledge base and offer remarkable transferability. However, this knowledge becomes outdated or insufficient over time. The challenge lies in continuously updating foundation models to accommodate novel information while retaining their original capabilities. Leveraging the fact that foundation models have initial knowledge on various tasks and domains, we propose a novel approach that, instead of updating all parameters equally, localizes the updates to a sparse set of parameters relevant to the …

abstract arxiv capabilities challenge cs.cv foundation however information knowledge knowledge base lies loss novel type update