Graph-Based Safe Support Vector Machine for Multiple Classes
Graph-Based Safe Support Vector Machine for Multiple Classes
复制标题
基于图的多类安全支持向量机
DOI：
10.1109/access.2018.2839187
复制
发表时间：
2018-01-01
期刊：
影响因子：
3.9
通讯作者：
Guan, Ling
中科院分区：
文献类型：
--
作者：
Wang, Song;Guo, Xin;Guan, Ling
半监督学习（SSL）利用有限的标记数据和大量的未标记数据，因其提高的学习性能而受到关注。然而，最近的研究表明，在某些情况下，使用未标记的数据可能会降低性能。因此，迫切需要开发安全的半监督学习方法来确定 SSL 是否应该应用于给定场景。本文提出了一种基于多类图的半监督支持向量机（SVM）的安全版本。首先，为了消除不良标签分配的影响，引入基于半监督SVM成本函数的标准来评估预测的标签分配。然后，根据标准选取 $m$ 个候选最佳标签分配。之后，设计多类安全策略来生成最终的标签分配，其性能绝不会比仅使用标记样本的方法差。几个基准数据集的实验结果验证了所提出技术的有效性。
Semi-supervised learning (SSL) utilizes limited labeled data and plenty of unlabeled data, and it has attracted attentions for its improved learning performance. However, recent studies have indicated that using unlabeled data, in some cases, could deteriorate the performance. Therefore, there’s an imminent need to develop safe semi-supervised learning methods to determine whether SSL should be applied for a given scenario. This paper proposes a safe version of multi-class graph-based semi-supervised support vector machine (SVM). At first, in order to eliminate the impact of bad label assignments, a criterion based on the cost function of semi-supervised SVM is introduced to evaluate the predicted label assignments. Then, $m$ candidate optimal label assignments are picked up by the criterion. After that, a multi-class safe strategy is designed to generate the final label assignment whose performance is never worse than that of the methods using only labeled samples. Experimental results on several benchmark data sets validate the effectiveness of the proposed technique.