Continual learning requires incremental compatibility with a sequence of tasks. However, the design of model architecture remains an open question: In general, learning all tasks with a shared set of parameters suffers from severe interference between tasks; while learning each task with a dedicated parameter subspace is limited by scalability. In this work, we theoretically analyze the generalization errors for learning plasticity and memory stability in continual learning, which can be uniformly upper-bounded by (1) discrepancy between task distributions, (2) flatness of loss landscape and (3) cover of parameter space. Then, inspired by the robust biological learning system that processes sequential experiences with multiple parallel compartments, we propose Cooperation of Small Continual Learners (CoSCL) as a general strategy for continual learning. Specifically, we present an architecture with a fixed number of narrower sub-networks to learn all incremental tasks in parallel, which can naturally reduce the two errors through improving the three components of the upper bound. To strengthen this advantage, we encourage to cooperate these sub-networks by penalizing the difference of predictions made by their feature representations. With a fixed parameter budget, CoSCL can improve a variety of representative continual learning approaches by a large margin (e.g., up to 10.64% on CIFAR-100-SC, 9.33% on CIFAR-100-RS, 11.45% on CUB-200-2011 and 6.72% on Tiny-ImageNet) and achieve the new state-of-the-art performance.

本文研究了在环境改变时如何使模型具有可持续发展能力，在理论层面上证明了增量学习的可行性，并提出了一种新的模型架构——Cooperation of Small Continual Learners (CoSCL)，该模型使用一组独立的子网络来学习所有的任务，有助于提高模型的泛化能力和记忆稳定性，并取得了新的最优性能。

CoSCL: 小型持续学习者的合作比大型学习者更加强大