Song Zixing, Yang Xiangli, Xu Zenglin, King Irwin
IEEE Trans Neural Netw Learn Syst. 2023 Nov;34(11):8174-8194. doi: 10.1109/TNNLS.2022.3155478. Epub 2023 Oct 27.
Semi-supervised learning (SSL) has tremendous value in practice due to the utilization of both labeled and unlabelled data. An essential class of SSL methods, referred to as graph-based semi-supervised learning (GSSL) methods in the literature, is to first represent each sample as a node in an affinity graph, and then, the label information of unlabeled samples can be inferred based on the structure of the constructed graph. GSSL methods have demonstrated their advantages in various domains due to their uniqueness of structure, the universality of applications, and their scalability to large-scale data. Focusing on GSSL methods only, this work aims to provide both researchers and practitioners with a solid and systematic understanding of relevant advances as well as the underlying connections among them. The concentration on one class of SSL makes this article distinct from recent surveys that cover a more general and broader picture of SSL methods yet often neglect the fundamental understanding of GSSL methods. In particular, a significant contribution of this article lies in a newly generalized taxonomy for GSSL under the unified framework, with the most up-to-date references and valuable resources such as codes, datasets, and applications. Furthermore, we present several potential research directions as future work with our insights into this rapidly growing field.
半监督学习（SSL）由于同时利用了有标签和无标签的数据，在实践中具有巨大价值。文献中一类重要的SSL方法，被称为基于图的半监督学习（GSSL）方法，是首先将每个样本表示为亲和图中的一个节点，然后，基于所构建图的结构推断无标签样本的标签信息。GSSL方法因其结构的独特性、应用的普遍性以及对大规模数据的可扩展性，在各个领域都展现出了优势。仅聚焦于GSSL方法，这项工作旨在为研究人员和从业者提供对相关进展以及它们之间潜在联系的扎实而系统的理解。专注于一类SSL使得本文有别于近期那些涵盖更广泛和全面的SSL方法图景但往往忽略对GSSL方法基本理解的综述。特别是，本文的一个重要贡献在于在统一框架下为GSSL提出了一种新的广义分类法，以及最新的参考文献和诸如代码、数据集及应用等有价值的资源。此外，我们给出了几个潜在的研究方向作为未来工作，并分享了我们对这个快速发展领域的见解。
