Open-world machine learning: A review and new outlooks
It tackles the problem of making machine learning models robust and adaptive in real-world, non-stationary environments for researchers and practitioners, though it is incremental as a review and outlook.
The paper reviews the emerging paradigm of open-world machine learning, which addresses the limitations of closed-world assumptions by focusing on rejecting unknowns, discovering novelties, and continual learning to enable models to adapt in dynamic environments, aiming to build more powerful AI systems.
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.