SPARC: Self-Paced Network Representation for Few-Shot Rare Category Characterization
SPARC: Self-Paced Network Representation for Few-Shot Rare Category Characterization
复制标题
DOI：
10.1145/3219819.3219968
复制
发表时间：
2018-07
期刊：
影响因子：
--
通讯作者：
Dawei Zhou;Jingrui He;Hongxia Yang;Wei Fan
中科院分区：
文献类型：
--
作者：
Dawei Zhou;Jingrui He;Hongxia Yang;Wei Fan
在大数据时代，从在线交易网络中的金融欺诈检测到社交网络中的新兴趋势检测，从计算机网络中的网络入侵检测到制造业中的故障检测，在许多高影响力的应用中，往往是那些罕见的类别受到极大关注。因此，稀有类别表征成为一项基本的学习任务，其目的是在有限的标签信息下准确表征稀有类别。罕见类别表征的独特挑战，即罕见类别与多数类别的不可分性，以及样本的多模态表示的可用性，提出了一个新的研究问题：我们如何学习一个突出的面向罕见类别的嵌入表示，使罕见样本在嵌入空间中与多数类别的样本很好地分离，从而便于后续的罕见类别表征？为了解决这个问题，受模拟人类认知机制的课程学习家族的启发，我们提出了一个名为SPARC的自进度框架，该框架通过从“容易”概念转向目标“困难”概念，以互惠的方式逐渐学习稀有的面向类别的网络表示和表征模型，从而促进对大量未标记示例的更可靠的标签传播。在各种真实数据上的实验结果表明，我们提出的SPARC算法：(1)在表示与大多数类别不可分离的稀有类别方面，比最先进的图嵌入方法有显著改进；(2)在稀有类别表征任务上优于现有方法。
In the era of big data, it is often the rare categories that are of great interest in many high-impact applications, ranging from financial fraud detection in online transaction networks to emerging trend detection in social networks, from network intrusion detection in computer networks to fault detection in manufacturing. As a result, rare category characterization becomes a fundamental learning task, which aims to accurately characterize the rare categories given limited label information. The unique challenge of rare category characterization, i.e., the non-separability nature of the rare categories from the majority classes, together with the availability of the multi-modal representation of the examples, poses a new research question: how can we learn a salient rare category oriented embedding representation such that the rare examples are well separated from the majority class examples in the embedding space, which facilitates the follow-up rare category characterization? To address this question, inspired by the family of curriculum learning that simulates the cognitive mechanism of human beings, we propose a self-paced framework named SPARC that gradually learns the rare category oriented network representation and the characterization model in a mutually beneficial way by shifting from the 'easy' concept to the target 'difficult' one, in order to facilitate more reliable label propagation to the large number of unlabeled examples. The experimental results on various real data demonstrate that our proposed SPARC algorithm: (1) shows a significant improvement over state-of-the-art graph embedding methods on representing the rare categories that are non-separable from the majority classes; (2) outperforms the existing methods on rare category characterization tasks.