中文摘要：

高斯过程（GPS）是一种良好的贝叶斯分类方法和回归过程，也可应用于半监督聚类方面，就此提出了一个新的算法：使用稀疏高斯过程回归模型来解决半监督二元分类问题，它是基于支持向量回归（SVR）和最大空间聚类（MMC）的半监督分类方法，此算法简单且易于实现，不同于SVR算法的稀疏解决方案。另外，超参数的估计也不再使用复杂的交叉验证技术，利用稀疏高斯回归模型有助于提高算法的可扩展性：使用合成的和真实世界的数据集初步验证了该算法的有效性。

英文摘要：

Gaussian Processes （GPS） are promising Bayesian methods for classification and regression problems.They have also been used for senti-supervised learning tasks.It is pointed out a new algorithm for solving semi-supervised binary classification problem using sparse GP regression（GPR） models.It is related to semi-supervised learning based on support vector regression（SVk） and maximum margin clustering. This algorithm is simple and easy to implement.lt gives a sparse solution unlike the SVR, based algorithm.Also,the hyperparameters are esti- mated without resorting to expensive cross-validation technique.Use of sparse GPR model helps in making the proposed algorithm scalable. Results on synthetic and real-world data sets demon-strate the efficacy of the new algorithm.