Metric Learning as a Service With Covariance Embedding
Metric Learning as a Service With Covariance Embedding
复制标题
DOI：
10.1109/tsc.2023.3266445
复制
发表时间：
2022-11
影响因子：
8.1
通讯作者：
Imam Mustafa Kamal;Hyerim Bae;Ling Liu
中科院分区：
文献类型：
--
作者：
Imam Mustafa Kamal;Hyerim Bae;Ling Liu
度量学习即服务（MLaaS）代表了服务计算研究社区和行业中处理复杂数据集的主要学习流之一。处理高维复杂数据集的一种常用方法是采用特征嵌入算法通过降维压缩数据，同时优化类内距离。为了为具有高维大数据的高性能人工智能应用程序创建可推广的MLaaS，需要通过有效优化类内和类间关系来实现鲁棒且有意义的嵌入空间表示。我们开发了一种新的MLaaS方法，该方法结合了协方差来表示嵌入空间中数据点之间线性关系的方向。我们的基于协方差的特征嵌入架构引入了三种不同但互补的映射函数：类内映射，类内与半类间映射，类内和类间映射。与传统的度量学习不同，我们的协方差嵌入增强方法在计算相似或不相似的度量时更具表达力和可解释性，并且可以捕获正、负或中性关系。我们的MLaaS框架通过支持降维和数据压缩方法的选择，确保了高效、可组合和可扩展的度量学习。使用各种基准数据集进行的实验表明，该模型可以获得更高的质量，更可分离，更有表现力的嵌入表示比现有的模型。
Metric learning as a service (MLaaS) represents one of the main learning streams to handle complex datasets in service computing research communities and industries. A common approach for dealing with high-dimensional and complex datasets is employing a feature embedding algorithm to compress data through dimension reduction while optimizing intra-class distance. To create generalizable MLaaS for high-performance artificial intelligence applications with high-dimensional Big Data, a robust and meaningful embedding space representation by efficiently optimizing both intra-class and inter-class relationships is required. We developed a novel MLaaS methodology that incorporates covariance to signify the direction of the linear relationship between data points in an embedding space. Our covariance-based feature embedding architecture introduces three different yet complementary mapping functions: inner-class mapping, intra-class with semi-inter-class mapping, and intra- and inter-class mapping. Unlike conventional metric learning, our covariance-embedding-enhanced approach is more expressive and explainable for computing similar or dissimilar measures and can capture positive, negative, or neutral relationships. Our MLaaS framework ensures efficient, composable, and extensible metric learning by supporting the selection of dimension reduction and data compression methods. Experiments conducted using various benchmark datasets demonstrate that the proposed model can obtain higher-quality, more separable, and more expressive embedding representations than existing models.