Deep state-space models (DSSMs) have gained popularity in recent years due to their potent modeling capacity for dynamic systems. However, existing DSSM works are limited to single-task modeling, which requires retraining with historical task data upon revisiting a forepassed task. To address this limitation, we propose continual learning DSSMs (CLDSSMs), which are capable of adapting to evolving tasks without catastrophic forgetting. Our proposed CLDSSMs integrate mainstream regularization-based continual learning (CL) methods, ensuring efficient updates with constant computational and memory costs for modeling multiple dynamic systems. We also conduct a comprehensive cost analysis of each CL method applied to the respective CLDSSMs, and demonstrate the efficacy of CLDSSMs through experiments on real-world datasets. The results corroborate that while various competing CL methods exhibit different merits, the proposed CLDSSMs consistently outperform traditional DSSMs in terms of effectively addressing catastrophic forgetting, enabling swift and accurate parameter transfer to new tasks.

翻译：深度状态空间模型（DSSMs）近年来因对动态系统强大的建模能力而受到广泛关注。然而，现有DSSM研究局限于单任务建模，当重新处理先前任务时需要利用历史任务数据重新训练模型。为解决这一局限，我们提出持续学习DSSMs（CLDSSMs），该模型无需灾难性遗忘即可适应不断演变的任务。所提出的CLDSSMs集成了主流基于正则化的持续学习（CL）方法，通过恒定的计算与存储成本确保对多个动态系统的高效更新。我们针对各CL方法在对应CLDSSMs中的应用进行了全面的成本分析，并通过真实世界数据集实验验证CLDSSMs的有效性。结果表明，尽管不同竞争性CL方法各具优势，但所提出的CLDSSMs在有效解决灾难性遗忘、实现快速准确的参数迁移至新任务方面，始终优于传统DSSMs。