Lifelong learning requires models that can continuously learn from sequential streams of data without suffering catastrophic forgetting due to shifts in data distributions. Deep learning models have thrived in the non-sequential learning paradigm; however, when used to learn a sequence of tasks, they fail to retain past knowledge and learn incrementally. We propose a novel approach to lifelong learning of language tasks based on meta-learning with sparse experience replay that directly optimizes to prevent forgetting. We show that under the realistic setting of performing a single pass on a stream of tasks and without any task identifiers, our method obtains state-of-the-art results on lifelong text classification and relation extraction. We analyze the effectiveness of our approach and further demonstrate its low computational and space complexity.
翻译:终身学习需要能够从连续数据流中不断学习而不会因为数据分布的变化而造成灾难性的遗忘的模型。深层次学习模型在非顺序学习模式中蓬勃发展;然而,当用于学习一系列任务时,它们未能保留过去的知识并逐步学习。我们提出一种基于元学习的终身学习语言任务的新办法,其基础是元学习,经验稀少的重现直接优化以防止遗忘。我们表明,在现实的一连串任务执行单一传球,而没有任何任务识别符的情况下,我们的方法在终身文本分类和关系提取方面获得了最先进的成果。我们分析了我们的方法的有效性,并进一步展示了它低的计算和空间复杂性。