AutoML 能为持续学习做什么？
What Can AutoML Do For Continual Learning?
AI总结：
本文探讨了 AutoML 在增量学习中的应用潜力，指出当前方法冻结架构和超参数的局限，并提出三个关键研究方向以使增量学习器更具动态性。
摘要：
这篇立场文件概述了 AutoML 在增量（持续）学习中的潜力，以鼓励该方向的更多研究。增量学习涉及从任务流和分布中纳入新数据，以学习增强的深度表示并更好地适应新任务。然而，增量学习的一个显著局限是，大多数当前技术在整个学习和适应过程中冻结了骨干架构、超参数以及学习任务的顺序和结构。我们坚信 AutoML 提供了有前景的解决方案来解决这些局限，使增量学习能够适应更多样化的现实世界任务。因此，本文不直接提出新方法，而是退一步提出问题：“AutoML 能为增量学习做什么？”我们概述了三个关键研究领域，这些领域有助于使增量学习器更具动态性，强调了以新颖方式应用 AutoML 方法的具体机会，以及 AutoML 研究的全新挑战。
英文摘要：
This position paper outlines the potential of AutoML for incremental (continual) learning to encourage more research in this direction. Incremental learning involves incorporating new data from a stream of tasks and distributions to learn enhanced deep representations and adapt better to new tasks. However, a significant limitation of incremental learners is that most current techniques freeze the backbone architecture, hyperparameters, and the order & structure of the learning tasks throughout the learning and adaptation process. We strongly believe that AutoML offers promising solutions to address these limitations, enabling incremental learning to adapt to more diverse real-world tasks. Therefore, instead of directly proposing a new method, this paper takes a step back by posing the question: "What can AutoML do for incremental learning?" We outline three key areas of research that can contribute to making incremental learners more dynamic, highlighting concrete opportunities to apply AutoML methods in novel ways as well as entirely new challenges for AutoML research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
