The pursuit of long-term autonomy mandates that machine learning models must continuously adapt to their changing environments and learn to solve new tasks. Continual learning seeks to overcome the challenge of catastrophic forgetting, where learning to solve new tasks causes a model to forget previously learnt information. Prior-based continual learning methods are appealing as they are computationally efficient and do not require auxiliary models or data storage. However, prior-based approaches typically fail on important benchmarks and are thus limited in their potential applications compared to their memory-based counterparts. We introduce Bayesian adaptive moment regularization (BAdam), a novel prior-based method that better constrains parameter growth, reducing catastrophic forgetting. Our method boasts a range of desirable properties such as being lightweight and task label-free, converging quickly, and offering calibrated uncertainty that is important for safe real-world deployment. Results show that BAdam achieves state-of-the-art performance for prior-based methods on challenging single-headed class-incremental experiments such as Split MNIST and Split FashionMNIST, and does so without relying on task labels or discrete task boundaries.

翻译：实现长期自主性要求机器学习模型必须持续适应不断变化的环境并学习解决新任务。持续学习旨在克服灾难性遗忘的挑战——即学习解决新任务会导致模型遗忘先前习得的信息。基于先验的持续学习方法因其计算高效且无需辅助模型或数据存储而备受关注。然而，与基于记忆的方法相比，基于先验的方法通常在重要基准测试中表现不佳，从而限制了其潜在应用范围。本文提出贝叶斯自适应矩正则化（BAdam），这是一种新型的基于先验的方法，能更好地约束参数增长，从而减少灾难性遗忘。该方法具有一系列优良特性：轻量级、无需任务标签、快速收敛，并提供对实际安全部署至关重要的校准不确定性。实验结果表明，在Split MNIST和Split FashionMNIST等具有挑战性的单头类增量实验中，BAdam在基于先验的方法中实现了最先进的性能，且不依赖于任务标签或离散的任务边界。