基于局部学习的半监督多标记分类算法

针对在求解半监督多标记分类问题时通常将其分解成若干个单标记半监督二类分类问题从而导致忽视类别之间内在联系的问题,提出基于局部学习的半监督多标记分类方法。该方法避开了多个单标记半监督二类分类问题的求解,采用“整体法”的研究思路,利用基于图的方法,引入基于样本的局部学习正则项和基于类别的拉普拉斯正则项,构建了问题的正则化框架。实验结果表明,所提算法具有较高的查全率和查准率。     

半监督正则化学习

研究半监督线性维数约减算法.与传统监督维数约减算法不同的是,半监督算法使用辅助信息和大量的无标号样本来达到更好的推广性能.在丰监督框架下,本文的目标是学习一个光滑、有判别力的子空间.明确地说,使用cannot-link成对约束来最大化不同类样本之间的距离,使用must-link成对约束来最小化相同类样本之间的距离;同时使用无标号样本的几何结构和投影向量的特征结构作为正则化项来引导维数约减过程.并且,所提出算法能容易处理样本外问题.实验结果验证了新算法的有效性.     

基于流形正则化的支持向量回归及应用

利用流形正则化的思想,围绕半监督学习,提出了一种针对回归问题的新算法。该算法基于流形上的正则化项和传统的正则化项相结合的方法,利用支持向量机回归已有的结果,解决半监督学习的回归问题,提高了泛化能力。通过数值试验,验证了该算法具有较好的泛化能力,对噪音具有较强的鲁棒性,与支持向量回归相比,具有更高的学习精度。     

基于流形正则化的分类与回归算法及应用

利用流形正则化的思想,围绕半监督学习,提出了一种针对流形正则化的模式分类和回归分析的新算法.该算法基于流形上的正则化项和传统的正则化项相结合的方法,利用支持向量机分类与回归已有的结果,解决半监督学习的分类与回归问题,提高了泛化能力.该算法实现简单,无需调用其他程序.通过数值试验,验证了该算法具有较好的泛化能力,对噪音具有较强的鲁棒性.且在分类问题上,该算法在输入极少数有标签样本时,也能保持较好的分类效果;在回归问题上,也具有较好的学习精度,尤其在输入带有噪音的流形数据上时,表现就更为突出.     

基于可变损失和流形正则化的生成对抗网络

针对生成对抗网络中鉴别器在少量标记样本上的分类精度较差以及对流形局部扰动的鲁棒性不足的问题,提出一种基于可变损失和流形正则化的生成对抗网络算法。当标记样本较少时,该算法在鉴别器中利用可变损失代替原有对抗损失以解决训练前期分类性能较差的鉴别器对半监督分类任务的不利影响。此外,在鉴别器可变损失的基础上加入流形正则项,通过惩罚鉴别器在流形上分类决策的变化提高鉴别器对局部扰动的鲁棒性。以生成样本的质量和半监督的分类精度作为算法的评价标准,并在数据集SVHN和CIFAR-10上完成了数值实验。与其他半监督算法的对比结果表明,该算法在使用少量带标记数据的情况下能得到质量更高的生成样本和精度更高的分类结果。     

基于图正则化的半监督非负矩阵分解

提出了一种基于图正则化的半监督非负矩阵分解算法（GSNMF）,克服了非负矩阵分解（NMF）、约束非负矩阵分解（CNMF）和图正则化非负矩阵分解（GNMF）方法忽略样本数据的局部几何结构或标签信息不足的缺陷,且NMF、CNMF和GNMF均为GSNMF的特例。也从理论上证明了GSNMF算法的收敛性。该算法对样本数据进行低维非负分解时,在图框架下既保持数据的几何结构,又利用已知样本的标签信息,在进行半监督学习时,同类样本能更好地聚集而类间距离尽可能大。在人脸数据库ORL、FERET和手写体数据库USPS上的仿真结果表明,相对于NMF及其一些改进算法,GSNMF均具有更高的聚类精度。     

结合均值漂移的基于图的半监督图像分类

针对基于图的半监督流形正则化图像分类算法需要大量无标记样本训练分类器,空间和时间复杂度高,甚至不能处理大规模图像,且对背景或目标复杂的图像分类错误率较高的问题,提出了结合均值漂移（mean shift）的基于图的半监督流形正则化图像分类算法。该方法对基于图的半监督流形正则化分类算法的改进主要体现在两方面,首先是通过mean shift算法对图像进行了平滑,以平滑后的图像作为分类对象;其次不是利用所有无标记样本,而是只采用少量无标记样本。实验结果表明:图像的平滑使得目标和背景区域的特征更为一致,从而利用较少的样本就可以提高分类器的正确率;同时大大降低了算法的复杂度,使得基于图的半监督分类算法用于分类大规模图像成为可能。     

拉普拉斯多层极速学习机

极速学习机不仅仅是有效的分类器,还能应用到半监督学习中.但是,半监督极速学习机和拉普拉斯光滑孪生支持向量机一样是一种浅层学习算法.深度学习实现了复杂函数的逼近并缓解了以前多层神经网络算法的局部最小性问题,目前在机器学习领域中引起了广泛的关注.多层极速学习机（ML-ELM）是根据深度学习和极速学习机的思想提出的算法,通过堆叠极速学习机-自动编码器算法（ELM-AE）构建多层神经网络模型,不仅实现复杂函数的逼近,并且训练过程中无需迭代,学习效率高.我们把流形正则化框架引入ML-ELM中提出拉普拉斯多层极速学习机算法（Lap-ML-ELM）.然而,ELM-AE不能很好的解决过拟合问题,针对这一问题我们把权值不确定引入ELM-AE中提出权值不确定极速学习机-自动编码器算法（WU-ELM-AE）,它学习到更为鲁棒的特征.最后,我们在前面两种算法的基础上提出权值不确定拉普拉斯多层极速学习机算法（WUL-ML-ELM）,它堆叠WU-ELM-AE构建深度模型,并且用流形正则化框架求取输出权值,该算法在分类精度上有明显提高并且不需花费太多的时间.实验结果表明,Lap-ML-ELM与WUL-ML-ELM都是有效的半监督学习算法.     

一种偏好于查询子流形的半监督图像检索算法

在基于反馈的图像检索中,由于被用户标记为相关和不相关的图像数较少,使得检索问题变成了一个典型的小样本问题.流形可表达数据在低维空间中的内在几何结构,流形正则化的目的是利用这种几何结构来约束解空间,以使最优解能反映数据本身的几何分布.为了解决反馈检索中的小样本问题,本文在流形正则化框架下提出一个新的半监督图像检索算法.在新算法中,流形正则化项只依赖于文中定义的查询子流形,而不依赖于数据集的全局结构.在两个图像集上的实验结果对比表明,本文提出的新算法在检索效果上优于现有的4种state-of-the-art算法.     

一种半监督协同训练的正则化算法

半监督学习是机器学习领域的研究热点。协同训练研究数据有多个特征集时的半监督学习问题。从正则化角度研究协同训练,利用假设空间的度量结构定义学习函数的光滑性和一致性,在每个视图内的学习过程中以函数光滑性为约束条件,在多个视图的协同学习过程中以函数一致性为约束条件,创新性地提出一种两个层次的正则化算法,同时使用函数的光滑性和一致性进行正则化。实验表明,该算法较仅使用光滑性或仅使用一致性的正则化方法在预测性能上有显著提高。     

A general learning framework using local and global regularization

In this paper, we propose a general learning framework based on local and global regularization. In the local regularization part, our algorithm constructs a regularized classifier for each data point using its neighborhood, while the global regularization part adopts a Laplacian regularizer to smooth the data labels predicted by those local classifiers. We show that such a learning framework can easily be incorporated into either unsupervised learning, semi-supervised learning, and supervised learning paradigm. Moreover, many existing learning algorithms can be derived from our framework. Finally we present some experimental results to show the effectiveness of our method.     

Neighborhood preserving regression for image retrieval

In content-based image retrieval (CBIR), relevance feedback has been proven to be a powerful tool for bridging the gap between low level visual features and high level semantic concepts. Traditionally, relevance feedback driven CBIR is often considered as a supervised learning problem where the user provided feedbacks are used to learn a distance metric or classification function. However, CBIR is intrinsically a semi-supervised learning problem in which the testing samples (images in the database) are present during the learning process. Moreover, when there are no sufficient feedbacks, these methods may suffer from the overfitting problem. In this paper, we propose a novel neighborhood preserving regression algorithm which makes efficient use of both labeled and unlabeled images. By using the unlabeled images, the geometrical structure of the image space can be incorporated into the learning system through a regularizer. Specifically, from all the functions which minimize the empirical loss on the labeled images, we select the one which best preserves the local neighborhood structure of the image space. In this way, our method can obtain a regression function which respects both semantic and geometrical structures of the image database. We present experimental evidence suggesting that our algorithm is able to use unlabeled data effectively for image retrieval.     

A Semi-supervised Learning Algorithm on Gaussian Mixture with Automatic Model Selection

In Gaussian mixture modeling, it is crucial to select the number of Gaussians for a sample set, which becomes much more difficult when the overlap in the mixture is larger. Under regularization theory, we aim to solve this problem using a semi-supervised learning algorithm through incorporating pairwise constraints into entropy regularized likelihood (ERL) learning which can make automatic model selection for Gaussian mixture. The simulation experiments further demonstrate that the presented semi-supervised learning algorithm (i.e., the constrained ERL learning algorithm) can automatically detect the number of Gaussians with a good parameter estimation, even when two or more actual Gaussians in the mixture are overlapped at a high degree. Moreover, the constrained ERL learning algorithm leads to some promising results when applied to iris data classification and image database categorization.     

基于半监督学习的多示例多标记E-MIMLSVM+算法

多示例多标记是一种新的机器学习框架,在该框架下一个对象用多个示例来表示,同时与多个类别标记相关联。MIMLSVM+算法将多示例多标记问题转化为一系列独立的二类分类问题,但是在退化过程中标记之间的联系信息会丢失,而E-MIMLSVM+算法则通过引入多任务学习技术对MIMLSVM+算法进行了改进。为了充分利用未标记样本来提高分类准确率,使用半监督支持向量机TSVM对E-MIMLSVM+算法进行了改进。通过实验将该算法与其他多示例多标记算法进行了比较,实验结果显示,改进算法取得了良好的分类效果。     

基于节点映射与标签数据构建的链接预测方法

为改进基于局部或全局信息相似性度量方法中存在的无法全面提取网络结构信息的问题,以及基于网络表示学习的方法不能对链接的不存在性进行度量的问题,提出一种结合节点向量化方法与机器学习分类算法的Net2Vec-CLP框架。使用具有重启机制的随机游走方法获得节点环境序列,将源网络信息转换成向量表示,在此基础上生成标签数据集,使用带sigmoid核映射方法的SVM模型进行二分类预测。实验结果表明,算法在Facebook数据集上较Node2Vec方法AUC值提高了2.47%,在其它数据集上也有可观测的优势。同时,结合二分类思想的方法,其能明确度量不存在链接关系的数据。     

一种半监督局部线性嵌入算法的文本分类方法*

针对局部线性嵌入算法（LLE）应用于非监督机器学习中的缺陷,将该算法与半监督思想相结合,提出了一种基于半监督局部线性嵌入算法的文本分类方法。通过使用文本数据的流形结构和少量的标签样本,将LLE中的距离矩阵采用分段形式进行调整;使用调整后的矩阵进行线性重建从而实现数据降维;针对半监督LLE中使用欧氏距离的缺点,采用高斯核函数将欧氏距离进行变换,并用新的核距离取代欧氏距离,提出了基于核的半监督局部线性嵌入算法;最后通过仿真实验验证了改进算法的有效性。     

Local margin based semi-supervised discriminant embedding for visual recognition

Most manifold learning algorithms adopt the k nearest neighbors function to construct the adjacency graph. However, severe bias may be introduced in this case if the samples are not uniformly distributed in the ambient space. In this paper a semi-supervised dimensionality reduction method is proposed to alleviate this problem. Based on the notion of local margin, we simultaneously maximize the separability between different classes and estimate the intrinsic geometric structure of the data by both the labeled and unlabeled samples. For high-dimensional data, a discriminant subspace is derived via maximizing the cumulative local margins. Experimental results on high-dimensional classification tasks demonstrate the efficacy of our algorithm.     

Perceptual relativity-based semi-supervised dimensionality reduction algorithm

As we all know, a well-designed graph tends to result in good performance for graph-based semi-supervised learning. Although most graph-based semi-supervised dimensionality reduction approaches perform very well on clean data sets, they usually cannot construct a faithful graph which plays an important role in getting a good performance, when performing on the high dimensional, sparse or noisy data. So this will generally lead to a dramatic performance degradation. To deal with these issues, this paper proposes a feasible strategy called relative semi-supervised dimensionality reduction (RSSDR) by utilizing the perceptual relativity to semi-supervised dimensionality reduction. In RSSDR, firstly, relative transformation will be performed over the training samples to build the relative space. It should be indicated that relative transformation improves the distinguishing ability among data points and diminishes the impact of noise on semi-supervised dimensionality reduction. Secondly, the edge weights of neighborhood graph will be determined through minimizing the local reconstruction error in the relative space such that it can preserve the global geometric structure as well as the local one of the data. Extensive experiments on face, UCI, gene expression, artificial and noisy data sets have been provided to validate the feasibility and effectiveness of the proposed algorithm with the promising results both in classification accuracy and robustness.