Affiliation:
1. National Key Laboratory for Novel Software Technology, Nanjing University , Nanjing 210023, China
Abstract
AbstractConventional machine learning studies generally assume close-environment scenarios where important factors of the learning process hold invariant. With the great success of machine learning, nowadays, more and more practical tasks, particularly those involving open-environment scenarios where important factors are subject to change, called open-environment machine learning in this article, are present to the community. Evidently, it is a grand challenge for machine learning turning from close environment to open environment. It becomes even more challenging since, in various big data tasks, data are usually accumulated with time, like streams, while it is hard to train the machine learning model after collecting all data as in conventional studies. This article briefly introduces some advances in this line of research, focusing on techniques concerning emerging new classes, decremental/incremental features, changing data distributions and varied learning objectives, and discusses some theoretical issues.
Funder
National Natural Science Foundation of China
Publisher
Oxford University Press (OUP)
Reference95 articles.
1. Open-world machine learning: applications, challenges, and opportunities;Parmar
2. Analyzing the robustness of open-world machine learning;Sehwag,2019
3. A comprehensive, application-oriented study of catastrophic forgetting in DNNs;Pfülb;7th International Conference on Learning Representations (ICLR),2019
4. A continual learning survey: defying forgetting in classification tasks;Delange;IEEE Trans Pattern Anal Mach Intell,2022
5. A brief introduction to weakly supervised learning;Zhou;Natl Sci Rev,2018
Cited by
41 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献