Learning multiple tasks sequentially without forgetting previous knowledge,
called Continual Learning(CL), remains a long-standing challenge for neural
networks. Most existing methods rely on additional network capacity or data
replay. In contrast, we introduce a novel approach which we refer to as
Recursive Gradient Optimization(RGO). RGO is composed of an iteratively updated
optimizer that modifies the gradient to minimize forgetting without data replay
and a virtual Feature Encoding Layer(FEL) that represents different long-term
structures with only task descriptors. Experiments demonstrate that RGO has
significantly better performance on popular continual classification benchmarks
when compared to the baselines and achieves new state-of-the-art performance on
20-split-CIFAR100(82.22%) and 20-split-miniImageNet(72.63%). With higher
average accuracy than Single-Task Learning(STL), this method is flexible and
reliable to provide continual learning capabilities for learning models that
rely on gradient descent.

本研究引入了一种名为 Recursive Gradient Optimization 的新方法，该方法不仅能够在没有数据重放的情况下修正梯度以减少遗忘，而且还具有虚拟特征编码层 (FEL)，该层只使用任务描述符即可表示不同的长期结构。实验表明，与基线相比，RGO 在流行的连续分类基准测试中表现显著更好，并在 20-split-CIFAR100 (82.22%) 和 20-split-miniImageNet (72.63%) 中取得了新的最佳性能。该方法比单任务学习（STL）具有更高的平均准确性，而且灵活可靠，在学习依赖于梯度下降的模型的连续学习方面具有潜在的应用价值。