arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.06004cs.CLcs.AIcs.LG
收藏

开放世界学习及其在产品分类中的应用

Open-world Learning and Application to Product Classification

University of Illinois at Chicago(伊利诺伊大学芝加哥分校);Tsinghua University(清华大学)

Hu Xu, Bing Liu, Lei Shu, P. Yu

摘要:

经典的监督学习做出了封闭世界的假设,这意味着在测试中看到的类必须在训练中看到。然而,在动态世界中,新的或看不见的类示例可能会不断出现。在这样的环境中工作的模型必须能够拒绝看不见的类(在训练中看不到或使用)。如果为看不见的类收集了足够的数据,系统应该逐步学习接受/分类它们。这种学习模式被称为开放世界学习(OWL)。现有的OWL方法都需要某种形式的重新训练,以接受或在整个模型中包含新类。在本文中,我们提出了一个元学习方法的问题。它的主要新颖之处在于,它只需要训练一个元分类器,当它们有足够的标记数据供元分类器使用时,元分类器可以不断接受新的类,并且还可以检测/拒绝未来看不见的类。不需要重新训练元分类器或覆盖所有旧类和新类的新的整体分类器。在测试中,该方法只使用所看到的类(包括新添加的类)的示例进行分类和拒绝。实验结果证明了新方法的有效性。

英文摘要:

Classic supervised learning makes the closed-world assumption, meaning that classes seen in testing must have been seen in training. However, in the dynamic world, new or unseen class examples may appear constantly. A model working in such an environment must be able to reject unseen classes (not seen or used in training). If enough data is collected for the unseen classes, the system should incrementally learn to accept/classify them. This learning paradigm is called open-world learning (OWL). Existing OWL methods all need some form of re-training to accept or include the new classes in the overall model. In this paper, we propose a meta-learning approach to the problem. Its key novelty is that it only needs to train a meta-classifier, which can then continually accept new classes when they have enough labeled data for the meta-classifier to use, and also detect/reject future unseen classes. No re-training of the meta-classifier or a new overall classifier covering all old and new classes is needed. In testing, the method only uses the examples of the seen classes (including the newly added classes) on-the-fly for classification and rejection. Experimental results demonstrate the effectiveness of the new approach.

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。

↑