Artificial neural networks face the well-known problem of catastrophic forgetting. What's worse, the degradation of previously learned skills becomes more severe as the task sequence increases, known as the long-term catastrophic forgetting. It is due to two facts: first, as the model learns more tasks, the intersection of the low-error parameter subspace satisfying for these tasks becomes smaller or even does not exist; second, when the model learns a new task, the cumulative error keeps increasing as the model tries to protect the parameter configuration of previous tasks from interference. Inspired by the memory consolidation mechanism in mammalian brains with synaptic plasticity, we propose a confrontation mechanism in which Adversarial Neural Pruning and synaptic Consolidation (ANPyC) is used to overcome the long-term catastrophic forgetting issue. The neural pruning acts as long-term depression to prune task-irrelevant parameters, while the novel synaptic consolidation acts as long-term potentiation to strengthen task-relevant parameters. During the training, this confrontation achieves a balance in that only crucial parameters remain, and non-significant parameters are freed to learn subsequent tasks. ANPyC avoids forgetting important information and makes the model efficient to learn a large number of tasks. Specifically, the neural pruning iteratively relaxes the current task's parameter conditions to expand the common parameter subspace of the task; the synaptic consolidation strategy, which consists of a structure-aware parameter-importance measurement and an element-wise parameter updating strategy, decreases the cumulative error when learning new tasks. The full source code is available at https://github.com/GeoX-Lab/ANPyC.
翻译:人工神经网络面临众所周知的灾难性遗忘问题。更糟糕的是,随着任务序列的增加,先前学到的技能的退化变得更加严重,被称为长期灾难性的遗忘。这是因为两个事实:首先,随着模型学习更多的任务,满足这些任务的低危险参数子空间的交汇会变小,甚至不存在;第二,当模型学习一项新的任务时,累积错误会随着模型试图保护先前任务的参数配置不受干扰而不断增加。在哺乳动物大脑中带有合成性塑料的记忆整合机制的启发下,我们建议了一个对抗机制,Adversarial Neal Prurning和合成整合(ANPyC)用来克服长期灾难性遗忘问题的交汇。神经调整作为长期压压压到与任务相关的参数,而新的合成合成整合则作为长期增强与任务相关的参数。在培训期间,这种对冲会达到一个仅关键参数的平衡,而Aversarial Pural Prurning 和同步整合(ANP) 的累积参数是用来在学习后期任务。Arental-rental任务中学习一个大型的默认任务。