Abstract
Conventional replay-based approaches to continual learning (CL) require, for each learning phase with new data, the replay of samples representing all of the previously learned knowledge in order to avoid catastrophic forgetting. Since the amount of learned knowledge grows over time in CL problems, generative replay spends an increasing amount of time just re-learning what is already known. In this proof-of-concept study, we propose a replay-based CL strategy that we term adiabatic replay (AR), which derives its efficiency from the (reasonable) assumption that each new learning phase is adiabatic, i.e., represents only a small addition to existing knowledge. Each new learning phase triggers a sampling process that selectively replays, from the body of existing knowledge, just such samples that are similar to the new data, in contrast to replaying all of it. Complete replay is not required since AR represents the data distribution by GMMs, which are capable of selectively updating their internal representation only where data statistics have changed. As long as additions are adiabatic, the amount of to-be-replayed samples need not to depend on the amount of previously acquired knowledge at all. We verify experimentally that AR is superior to state-of-the-art deep generative replay using VAEs.
Abstract (translated)
传统的重放基于学习的方法(CL)要求,在每个新的学习阶段中,使用新数据来重放代表以前学到的所有知识样本,以避免灾难性遗忘。由于CL问题中学到的知识量随着时间不断增加,生成回放花费越来越多的时间只是简单地重新学习已经学到的知识。在这个概念验证研究中,我们提出了一种基于重放的学习方法,我们称之为adiabatic重放(AR),其效率来源于(合理的)假设每个新的学习阶段只是对现有的知识进行微小的增加。每个新的学习阶段触发一个选择性采样过程,从现有的知识主体中选择性地重放与新数据相似的样本,而不像全部重放。由于AR代表GMMs对数据的分布,它们只能选择性地更新内部表示只有在数据统计量发生变化时才能进行。只要添加是adiabatic的,即将要重放的数据数量与以前学到的知识量无关。我们实验证实,AR比使用VAEs的最先进的深度生成回放方法优越。
URL
https://arxiv.org/abs/2303.13157