Open-World Classification or Machine Learning
(Open Classification or Open Learning)
A form of Lifelong Learning
"Lifelong Machine Learning."
by Z. Chen and B. Liu, Morgan & Claypool Publishers, November 2016.
- A section in chapter 3 focuses on open world learning
- A chatbot or self-driving car cannot learn during chatting or driving in the open envoronment is not intelligent.
Open world machine learning (a.k.a. open world classification or open classification) is getting very important as the learning agent is increasingly working in the real-life open and dynamic environment, e.g., chatbots and self-driving cars. We can no longer make the closed world assumption (Fei and Liu 2016), which is made by the classic machine learning paradigm.
Most existing research on supervised learning or classification makes the closed world assumption, which focuses on designing accurate classifiers under the assumption that all test classes are known at training time. A more realistic scenario is to expect unseen classes during testing (open world). In this case, the goal is to design a learning system that classifies data of the known classes into their respective classes and also to reject/detect instances from unknown classes. This problem is called open-world classification. Apart from detecting the unseen classes, we also want to incrementally learn the new classes. In fact, an open world learner should be able to do the following:
- traditional close-world classification (assuming test instances are from only the training/seen classes),
- detecting or rejecting instances of unseen classes - not seen in training (the DOC algorithm (EMNLP-2017) is very powerful for this task for both text and images),
- autmatically detecting unseen classes in the rejected instances, and
- incrementally learning the new/unseen classes.
In the process, the system accumulates more and more knowledge (Fei et al., 2016).
The learner is self-motivated and it knows what it does and does not know.
TextBook: Zhiyuan Chen and Bing Liu. Lifelong Machine Learning. Morgan & Claypool, 2016.
- Lei Shu, Hu Xu, Bing Liu. Unseen Class Discovery in Open-world Classification. arXiv:1801.05609 [cs.LG], 2018.
- Lei Shu, Hu Xu, Bing Liu. DOC: Deep Open Classification of Text Documents. Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP-2017, oral presentation short paper), September 7–11, 2017, Copenhagen, Denmark.
- Geli Fei, Shuai Wang, and Bing Liu. 2016. Learning Cumulatively to Become More Knowledgeable. Proceedings of SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD-2016), August 13-17, San Francisco, USA.
- Geli Fei, and Bing Liu. 2016. Breaking the Closed World Assumption in Text Classification. Proceedings of NAACL-HLT 2016 , June 12-17, San Diego, USA.
Created on Jan 24, 2018 by Bing Liu.