论文标题
通过递归梯度优化持续学习
Continual Learning with Recursive Gradient Optimization
论文作者
论文摘要
依次学习多个任务而没有忘记以前的知识（CL），仍然是神经网络的长期挑战。大多数现有方法依赖于其他网络容量或数据重播。相比之下，我们引入了一种新型方法，我们将其称为递归梯度优化（RGO）。 RGO由迭代更新的优化器组成，该优化器可修改梯度以最大程度地减少忘记而无需数据重播，而虚拟特征编码层（FEL）代表只有任务描述符的不同长期结构。实验表明，与基准相比，RGO在流行的持续分类基准上的性能明显更好，并且在20速度-CIFAR100（82.22％）和20阶段的Miniimagenet（72.63％）上实现了新的最先进的性能。该方法具有比单任务学习（STL）更高的平均精度（STL），可灵活且可靠，可以为依赖梯度下降的学习模型提供持续的学习能力。
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.
