Abstract
Continual learning on sequential data is critical for many machine learning (ML) deployments. Unfortunately, LSTM networks, which are commonly used to learn on sequential data, suffer from catastrophic forgetting and are limited in their ability to learn multiple tasks continually. We discover that catastrophic forgetting in LSTM networks can be overcome in two novel and readily-implementable ways -- separating the LSTM memory either for each task or for each target label. Our approach eschews the need for explicit regularization, hypernetworks, and other complex methods. We quantify the benefits of our approach on recently-proposed LSTM networks for computer memory access prefetching, an important sequential learning problem in ML-based computer system optimization. Compared to state-of-the-art weight regularization methods to mitigate catastrophic forgetting, our approach is simple, effective, and enables faster learning. We also show that our proposal enables the use of small, non-regularized LSTM networks for complex natural language processing in the offline learning scenario, which was previously considered difficult.
Abstract (translated)
对Sequential数据进行持续学习对于许多机器学习(ML)部署是至关重要的。不幸的是，LSTM网络，通常用于对Sequential数据进行学习，存在灾难性遗忘，并且其持续学习能力受到限制。我们发现，LSTM网络的灾难性遗忘可以通过两个新颖且易于实现的方法来解决——分别对每个任务或每个目标标签的LSTM记忆进行分离。我们的方法和避免使用显式正则化、超网络和其他复杂的方法。我们量化了我们对最近提出的LSTM网络用于计算机内存访问预加载的研究所带来的好处，这是一个在基于机器学习的计算机系统优化中非常重要的Sequential学习问题。与旨在缓解灾难性遗忘的先进的权重正则化方法相比，我们的方法和简单、有效，并且能够加速学习。我们还展示了，我们的建议使可以使用小型未正则化的LSTM网络在离线学习场景中进行复杂的自然语言处理，这在以前被认为是困难的。
URL
https://arxiv.org/abs/2305.17244
