arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.09202cs.LGcs.AI
收藏

属性序列的一次性学习

One-Shot Learning on Attributed Sequences

Worcester Polytechnic Institute(伍斯特理工学院);Amadeus IT Group(艾玛迪斯信息技术集团)

Zhongfang Zhuang, Xiangnan Kong, Elke Rundensteiner, Aditya Arora, Jihane Zouaoui

摘要:

在过去的十年中,一次性学习已经成为一个重要的研究课题,并有许多实际应用。单次学习的目标是当每个类只有一个标记示例时对未标记的实例进行分类。传统的一次性学习问题设置主要集中在已经在特征空间中的数据(如图像)上。然而,在现实世界的应用程序中的数据实例往往更复杂,特征向量可能是不可用的。在本文中,我们研究了属性序列上的一次性学习问题,其中每个实例由一组属性组成(例如,用户简档)和分类项目序列(例如,点击流)。这个问题对于从欺诈预防到网络入侵检测的各种实际应用都很重要。这个问题比传统的一次性学习更具挑战性,因为属性和序列之间存在依赖关系。我们设计了一个深度学习框架OLAS来解决这个问题。建议的OLAS利用一个孪生网络来概括成对属性序列的例子的功能。在真实数据集上的实验结果表明,在各种参数设置下,所提出的OLAS方法的性能都优于现有的方法。

英文摘要:

One-shot learning has become an important research topic in the last decade with many real-world applications. The goal of one-shot learning is to classify unlabeled instances when there is only one labeled example per class. Conventional problem setting of one-shot learning mainly focuses on the data that is already in feature space (such as images). However, the data instances in real-world applications are often more complex and feature vectors may not be available. In this paper, we study the problem of one-shot learning on attributed sequences, where each instance is composed of a set of attributes (e.g., user profile) and a sequence of categorical items (e.g., clickstream). This problem is important for a variety of real-world applications ranging from fraud prevention to network intrusion detection. This problem is more challenging than conventional one-shot learning since there are dependencies between attributes and sequences. We design a deep learning framework OLAS to tackle this problem. The proposed OLAS utilizes a twin network to generalize the features from pairwise attributed sequence examples. Empirical results on real-world datasets demonstrate the proposed OLAS can outperform the state-of-the-art methods under a rich variety of parameter settings.

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。

↑