Learning Deep Latent Spaces for Multi-Label Classification
This addresses the practical challenge of predicting multiple labels per instance in machine learning, with incremental improvements in handling label dependencies and missing labels.
The authors tackled multi-label classification by proposing a novel deep neural network model, Canonical Correlated AutoEncoder (C2AE), which integrates canonical correlation analysis and autoencoder architectures to create a deep latent space and uses a label-correlation sensitive loss function, achieving favorable performance against state-of-the-art methods on multiple datasets.
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.