Learning Deep Latent Spaces for Multi-Label Classification
Learning Deep Latent Spaces for Multi-Label Classification
复制标题
DOI：
--
复制
发表时间：
2017-07
期刊：
影响因子：
--
通讯作者：
Chih-Kuan Yeh;Wei-Chieh Wu;Wei-Jen Ko;Y. Wang
中科院分区：
文献类型：
--
作者：
Chih-Kuan Yeh;Wei-Chieh Wu;Wei-Jen Ko;Y. Wang
多标签分类是机器学习相关领域中一项实用但具有挑战性的任务，因为它需要为每个输入实例预测多个标签类别。我们提出了一种基于深度神经网络（DNN）的新颖模型，即规范相关自动编码器（C2AE）来解决此任务。为了更好地关联特征和标签域数据以改进分类，我们通过导出深层潜在空间来独特地执行联合特征和标签嵌入，然后引入标签相关敏感损失函数来恢复预测的标签输出。我们的 C2AE 是通过集成规范相关分析和自动编码器的 DNN 架构来实现的，它允许端到端学习和预测，并能够利用标签依赖性。此外，我们的 C2AE 可以轻松扩展以解决缺少标签的学习问题。我们对不同规模的多个数据集的实验证实了我们提出的方法的有效性和鲁棒性，该方法被证明比最先进的多标签分类方法表现更好。
Multi-label classification is a practical yet challenging task in machine learning related fields, since it requires the prediction of more than one label category for each input instance. We propose a novel deep neural networks (DNN) based model, Canonical Correlated AutoEncoder (C2AE), for solving this task. Aiming at better relating feature and label domain data for improved classification, we uniquely perform joint feature and label embedding by deriving a deep latent space, followed by the introduction of label-correlation sensitive loss function for recovering the predicted label outputs. Our C2AE is achieved by integrating the DNN architectures of canonical correlation analysis and autoencoder, which allows end-to-end learning and prediction with the ability to exploit label dependency. Moreover, our C2AE can be easily extended to address the learning problem with missing labels. Our experiments on multiple datasets with different scales confirm the effectiveness and robustness of our proposed method, which is shown to perform favorably against state-of-the-art methods for multi-label classification.