A multi-scheme semi-supervised regression approach
A multi-scheme semi-supervised regression approach
复制标题
DOI：
10.1016/j.patrec.2019.07.022
复制
发表时间：
2019-07-01
影响因子：
5.1
通讯作者：
Sgarbas, Kyriakos
中科院分区：
文献类型：
--
作者：
Fazakis, Nikos;Karlos, Stamatis;Sgarbas, Kyriakos
大量数据的产生增加了应用机器学习（ML）和模式识别（PR）方法的必要性，这些方法可以执行准确的预测性能，而无需花费大量人力来收集和准备必要的数据。请记住，在监督方法的学习阶段，注释实例是最耗时的过程之一，半监督学习（SSL）方案的作用，它利用标记和未标记的数据，是完全升级，特别是考虑到现实世界的情况。通过这种方案提供的关于组合各种学习者以通过未标记的实例挖掘有用信息的灵活性允许产生这些方案的几个变体。因此，构建通用的方法，可以实现强大的学习行为的问题，源于不同的科学领域是当前研究的目标。通过这项工作，我们的贡献是多方案半监督回归方法（MSSRA）的建议，该方法检查了有关每个包含的学习器的输出的一些定义明确的条件，并将其决策提供给元级学习器以产生最终的预测。在25个知名数据集上的实验结果证明了该算法相对于元级学习器的监督版本和两种最先进的半监督回归（SSR）算法具有更好的泛化性能。(C)2019 Elsevier B.V.版权所有。
The production of vast amounts of data has increased the necessity of applying Machine Learning (ML) and Pattern Recognition (PR) methods that could perform accurate predictive performance without demanding much human effort for collecting and preparing the necessary data. Keeping in mind that annotating instances is one of the most time-consuming procedures during the learning phase of supervised approaches, the role of Semi-supervised Learning (SSL) schemes, which exploit both labeled and unlabeled data, is totally upgraded considering especially the real-word scenarios. The flexibility that is offered through such schemes about combining various learners for mining useful information through unlabeled instances allows the production of several variants of these schemes. Thus, the construction of generic approaches that could achieve robust learning behavior over problems that stem from different scientific fields is the target of current research. Our contribution through this work is the proposal of a Multi-scheme Semi-supervised regression approach (MSSRA) that examines some well-defined conditions about the outputs of each contained learner and provides its decisions to a meta-level learner to produce the final predictions. The results over twenty-five well-known datasets prove the better generalization behavior of the proposed algorithm against the supervised version of the meta-level learner and two state-of-the-art semi-supervised regression (SSR) algorithms. (C) 2019 Elsevier B.V. All rights reserved.