学习低秩特征表示：在持续学习中实现稳定性与可塑性的更佳权衡
Learning a Low-Rank Feature Representation: Achieving Better Trade-Off between Stability and Plasticity in Continual Learning
AI总结：
针对持续学习中网络稳定性与可塑性的权衡问题，提出LRFR训练算法，通过在过往任务特征矩阵零空间优化参数、低秩学习特征表示提升可塑性，在基准数据集上性能优于现有最优方法。
摘要：
在持续学习中，网络在按任务序列训练时会面临稳定性与可塑性之间的权衡问题。为在不牺牲稳定性的前提下提升可塑性，我们提出了一种名为LRFR的新型训练算法。该方法在过往任务特征表示矩阵的零空间中优化网络参数，以保证稳定性。同时，在训练单个任务时，我们审慎地仅选择网络每一层中的神经元子集，以低秩形式学习过往任务的特征表示矩阵。这会在为后续任务设计网络参数时增大零空间的维度，从而增强可塑性。我们使用CIFAR-100和TinyImageNet作为持续学习的基准数据集，所提方法的性能始终优于当前最优方法。
英文摘要：
In continual learning, networks confront a trade-off between stability and plasticity when trained on a sequence of tasks. To bolster plasticity without sacrificing stability, we propose a novel training algorithm called LRFR. This approach optimizes network parameters in the null space of the past tasks' feature representation matrix to guarantee the stability. Concurrently, we judiciously select only a subset of neurons in each layer of the network while training individual tasks to learn the past tasks' feature representation matrix in low-rank. This increases the null space dimension when designing network parameters for subsequent tasks, thereby enhancing the plasticity. Using CIFAR-100 and TinyImageNet as benchmark datasets for continual learning, the proposed approach consistently outperforms state-of-the-art methods.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
