论文标题
基于节点的自适应组稀疏正则化持续学习
Continual Learning with Node-Importance based Adaptive Group Sparse Regularization
论文作者
论文摘要
我们使用两种基于组的基于稀疏性的惩罚，提出了一种基于正则化的持续学习方法，称为基于自适应群的持续学习（AGS-CL）。当学习每个节点的重要性时，我们的方法选择性地采用了两种惩罚，在学习每个新任务后，它会自适应地更新。通过利用近端梯度下降方法进行学习，可以保证模型的确切稀疏性和冻结，因此，随着学习的继续，学习者可以明确控制模型能力。此外，作为一个关键细节，我们在学习每个任务后重新定位了与不重要的节点相关的权重，以防止导致灾难性遗忘的负转移，并促进对新任务的有效学习。在整个广泛的实验结果中，我们表明我们的AGS-CL使用更少的额外记忆空间来存储正则化参数，并且在对监督和加强学习任务的代表性持续学习基准方面的代表性持续学习基准测试大大优于几个最先进的基准。
We propose a novel regularization-based continual learning method, dubbed as Adaptive Group Sparsity based Continual Learning (AGS-CL), using two group sparsity-based penalties. Our method selectively employs the two penalties when learning each node based its the importance, which is adaptively updated after learning each new task. By utilizing the proximal gradient descent method for learning, the exact sparsity and freezing of the model is guaranteed, and thus, the learner can explicitly control the model capacity as the learning continues. Furthermore, as a critical detail, we re-initialize the weights associated with unimportant nodes after learning each task in order to prevent the negative transfer that causes the catastrophic forgetting and facilitate efficient learning of new tasks. Throughout the extensive experimental results, we show that our AGS-CL uses much less additional memory space for storing the regularization parameters, and it significantly outperforms several state-of-the-art baselines on representative continual learning benchmarks for both supervised and reinforcement learning tasks.
