Learning Deep Latent Space for Multi-Label Classification
By Chih-Kuan Yeh, Wei-Chieh Wu, Wei-Jen Ko, Yu-Chiang Frank Wang. 2017
160 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Francisco Herrera
- Salvador Garcia
- M. J. Jesús
- Francisco Charte
- Tianlu Wang
- Vicente Ordonez
- Yanjun Qi
- Chen Chen
Citations in the corpus
- A practical tutorial on autoencoders for nonlinear feature fusion: Taxonomy, models, software and guidelines (2018, methodology): “In [116] the authors propose an AE-based method named C2AE (Canonical Correlated AutoEncoder), aimed to learn a compressed feature space while establishing relationships between the input and output spaces.”
- General Multi-label Image Classification with Transformers (2020, background): “(2) Shared Embedding Space: The second group learns to project input features and output labels into a shared latent embedding space [57, 3].”
- Two-Stage Label Embedding via Neural Factorization Machine for Multi-Label Classification (2019, methodology): “To handle this problem, we adapt the idea of (Yeh et al. 2017) and introduce a multi-layer decoding network h D : where s i , W di , b di , σ i denote the output vector, weight matrix, bias vector and activation function for the i -th layer respectively.”
- Probabilistic Label Tree for Streaming Multi-Label Learning (2021, methodology): “• C2AE [31] is the state-of-the-art deep learning method for multi-label classification, which integrates the DNN architectures of canonical correlation analysis and auto-encoder to learn the deep latent space.”