Learning Deep Latent Spaces for Multi-Label Classification
Journal
The 31st AAAI Conference on Artificial Intelligence (AAAI-17)
Date Issued
2017
Author(s)
Abstract
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. Copyright © 2017, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
Other Subjects
Artificial intelligence; Deep learning; Deep neural networks; Learning systems; Canonical correlation analysis; Label correlations; Label dependencies; Learning problem; Loss functions; Multi label classification; Multiple data sets; State-of-the-art methods; Classification (of information)
Type
conference paper