arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.01759cs.LGcs.CV
收藏

开放世界机器学习:综述与新展望

Open-world machine learning: A review and new outlooks

Centre for Artificial Intelligence and Robotics, Hong Kong Institute of Science and Innovation, Chinese Academy of Sciences(人工智能与机器人中心,香港科学与创新研究院,中国科学院);State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation of Chinese Academy of Sciences(多模态人工智能系统国家重点实验室,中国科学院自动化研究所);College of Computing and Data Science, Nanyang Technological University(计算与数据科学学院,南洋理工大学)

Fei Zhu, Shijie Ma, Zhen Cheng, Xu-Yao Zhang, Zhaoxiang Zhang, Dacheng Tao, Cheng-Lin Liu

AI总结:

本文综述开放世界机器学习,统一探讨未知拒绝、新奇发现与持续学习,总结挑战、基准与性能,并展望未来方向,以推动更安全、可进化的AI系统发展。

摘要:

机器学习在许多应用中取得了显著成功。然而,现有研究大多基于封闭世界假设,该假设认为环境是静态的,且模型一旦部署便固定不变。在许多现实世界应用中,这一基本且相当天真的假设可能不成立,因为开放环境是复杂、动态且充满未知的。在这种情况下,拒绝未知、发现新奇事物,然后持续学习它们,可以使模型像生物系统一样安全且不断进化。本文通过在一个统一范式中研究未知拒绝、新奇发现和持续学习,呈现了开放世界机器学习的整体视角。详细讨论了当前方法的挑战、原则和局限性。此外,总结了广泛使用的基准、指标和性能。最后,我们讨论了该领域进一步发展的几个潜在方向。通过对新兴的开放世界机器学习范式提供全面介绍,本文旨在帮助研究人员在其各自领域构建更强大的人工智能系统,并促进通用人工智能的发展。

英文摘要:

Machine learning has achieved remarkable success in many applications. However, existing studies are largely based on the closed-world assumption, which assumes that the environment is stationary, and the model is fixed once deployed. In many real-world applications, this fundamental and rather naive assumption may not hold because an open environment is complex, dynamic, and full of unknowns. In such cases, rejecting unknowns, discovering novelties, and then continually learning them, could enable models to be safe and evolve continually as biological systems do. This article presents a holistic view of open-world machine learning by investigating unknown rejection, novelty discovery, and continual learning in a unified paradigm. The challenges, principles, and limitations of current methodologies are discussed in detail. Furthermore, widely used benchmarks, metrics, and performances are summarized. Finally, we discuss several potential directions for further progress in the field. By providing a comprehensive introduction to the emerging open-world machine learning paradigm, this article aims to help researchers build more powerful AI systems in their respective fields, and to promote the development of artificial general intelligence.

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。

↑