In neural networks, continual learning results in gradient interference among sequential tasks, leading to catastrophic forgetting of old tasks while learning new ones. This issue is addressed in recent methods by storing the important gradient spaces for old tasks and updating the model orthogonally during new tasks. However, such restrictive orthogonal gradient updates hamper the learning capability of the new tasks resulting in sub-optimal performance. To improve new learning while minimizing forgetting, in this paper we propose a Scaled Gradient Projection (SGP) method, where we combine the orthogonal gradient projections with scaled gradient steps along the important gradient spaces for the past tasks. The degree of gradient scaling along these spaces depends on the importance of the bases spanning them. We propose an efficient method for computing and accumulating importance of these bases using the singular value decomposition of the input representations for each task. We conduct extensive experiments ranging from continual image classification to reinforcement learning tasks and report better performance with less training overhead than the state-of-the-art approaches.

翻译：在神经网络中，持续学习会导致顺序任务间的梯度干扰，从而在学习新任务时引发对旧任务的灾难性遗忘。近期方法通过存储旧任务的重要梯度空间，并在新任务训练期间进行正交更新来解决该问题。然而，这种限制性的正交梯度更新会削弱新任务的学习能力，导致次优性能。为在学习新任务时最小化遗忘的同时提升学习效果，本文提出一种缩放梯度投影（SGP）方法，将正交梯度投影与沿旧任务重要梯度空间的缩放梯度步骤相结合。沿这些空间的梯度缩放程度取决于构成它们的基的重要性。我们提出基于各任务输入表示的奇异值分解来高效计算并累积这些基重要性的方法。通过在持续图像分类到强化学习任务等广泛实验中的验证，该方法在减少训练开销的同时，取得了优于现有最优方法的性能表现。